Repository: haotian-liu/LLaVA Branch: main Commit: c121f0432da2 Files: 140 Total size: 459.8 KB Directory structure: gitextract_4r0bw0y0/ ├── .devcontainer/ │ ├── Dockerfile │ ├── devcontainer.env │ ├── devcontainer.json │ └── postCreateCommand.sh ├── .dockerignore ├── .editorconfig ├── .gitattributes ├── .github/ │ └── ISSUE_TEMPLATE/ │ ├── 1-usage.yaml │ ├── 2-feature-request.yaml │ ├── 3-question.yaml │ └── 4-discussion.yaml ├── .gitignore ├── LICENSE ├── README.md ├── cog.yaml ├── docs/ │ ├── Customize_Component.md │ ├── Data.md │ ├── Evaluation.md │ ├── Finetune_Custom_Data.md │ ├── Intel.md │ ├── LLaVA_Bench.md │ ├── LLaVA_from_LLaMA2.md │ ├── LoRA.md │ ├── MODEL_ZOO.md │ ├── ScienceQA.md │ ├── Windows.md │ └── macOS.md ├── llava/ │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── eval/ │ │ ├── eval_gpt_review.py │ │ ├── eval_gpt_review_bench.py │ │ ├── eval_gpt_review_visual.py │ │ ├── eval_pope.py │ │ ├── eval_science_qa.py │ │ ├── eval_science_qa_gpt4.py │ │ ├── eval_science_qa_gpt4_requery.py │ │ ├── eval_textvqa.py │ │ ├── generate_webpage_data_from_table.py │ │ ├── m4c_evaluator.py │ │ ├── model_qa.py │ │ ├── model_vqa.py │ │ ├── model_vqa_loader.py │ │ ├── model_vqa_mmbench.py │ │ ├── model_vqa_science.py │ │ ├── qa_baseline_gpt35.py │ │ ├── run_llava.py │ │ ├── summarize_gpt_review.py │ │ └── webpage/ │ │ ├── index.html │ │ ├── script.js │ │ └── styles.css │ ├── mm_utils.py │ ├── model/ │ │ ├── __init__.py │ │ ├── apply_delta.py │ │ ├── builder.py │ │ ├── consolidate.py │ │ ├── language_model/ │ │ │ ├── llava_llama.py │ │ │ ├── llava_mistral.py │ │ │ └── llava_mpt.py │ │ ├── llava_arch.py │ │ ├── make_delta.py │ │ ├── multimodal_encoder/ │ │ │ ├── builder.py │ │ │ └── clip_encoder.py │ │ ├── multimodal_projector/ │ │ │ └── builder.py │ │ └── utils.py │ ├── serve/ │ │ ├── __init__.py │ │ ├── cli.py │ │ ├── controller.py │ │ ├── gradio_web_server.py │ │ ├── model_worker.py │ │ ├── register_worker.py │ │ ├── sglang_worker.py │ │ └── test_message.py │ ├── train/ │ │ ├── llama_flash_attn_monkey_patch.py │ │ ├── llama_xformers_attn_monkey_patch.py │ │ ├── llava_trainer.py │ │ ├── train.py │ │ ├── train_mem.py │ │ └── train_xformers.py │ └── utils.py ├── playground/ │ └── data/ │ └── prompts/ │ ├── complex_reasoning/ │ │ ├── 000_caps.txt │ │ ├── 000_conv.txt │ │ ├── 001_caps.txt │ │ ├── 001_conv.txt │ │ ├── 002_caps.txt │ │ ├── 002_conv.txt │ │ └── system_message.txt │ ├── conversation/ │ │ ├── 000_caps.txt │ │ ├── 000_conv.txt │ │ ├── 001_caps.txt │ │ ├── 001_conv.txt │ │ └── system_message.txt │ └── detail_description/ │ ├── 000_caps.txt │ ├── 000_conv.txt │ ├── 001_caps.txt │ ├── 001_conv.txt │ ├── 002_caps.txt │ ├── 002_conv.txt │ └── system_message.txt ├── predict.py ├── pyproject.toml └── scripts/ ├── convert_gqa_for_eval.py ├── convert_mmbench_for_submission.py ├── convert_mmvet_for_eval.py ├── convert_seed_for_submission.py ├── convert_sqa_to_llava.py ├── convert_sqa_to_llava_base_prompt.py ├── convert_vizwiz_for_submission.py ├── convert_vqav2_for_submission.py ├── extract_mm_projector.py ├── finetune.sh ├── finetune_full_schedule.sh ├── finetune_lora.sh ├── finetune_qlora.sh ├── finetune_sqa.sh ├── merge_lora_weights.py ├── pretrain.sh ├── pretrain_xformers.sh ├── sqa_eval_batch.sh ├── sqa_eval_gather.sh ├── upload_pypi.sh └── v1_5/ ├── eval/ │ ├── gqa.sh │ ├── llavabench.sh │ ├── mmbench.sh │ ├── mmbench_cn.sh │ ├── mme.sh │ ├── mmvet.sh │ ├── pope.sh │ ├── qbench.sh │ ├── qbench_zh.sh │ ├── seed.sh │ ├── sqa.sh │ ├── textvqa.sh │ ├── vizwiz.sh │ └── vqav2.sh ├── finetune.sh ├── finetune_lora.sh ├── finetune_task.sh ├── finetune_task_lora.sh └── pretrain.sh ================================================ FILE CONTENTS ================================================ ================================================ FILE: .devcontainer/Dockerfile ================================================ FROM mcr.microsoft.com/devcontainers/base:ubuntu-20.04 SHELL [ "bash", "-c" ] # update apt and install packages RUN apt update && \ apt install -yq \ ffmpeg \ dkms \ build-essential # add user tools RUN sudo apt install -yq \ jq \ jp \ tree \ tldr # add git-lfs and install RUN curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash && \ sudo apt-get install -yq git-lfs && \ git lfs install ############################################ # Setup user ############################################ USER vscode # install azcopy, a tool to copy to/from blob storage # for more info: https://learn.microsoft.com/en-us/azure/storage/common/storage-use-azcopy-blobs-upload#upload-a-file RUN cd /tmp && \ wget https://azcopyvnext.azureedge.net/release20230123/azcopy_linux_amd64_10.17.0.tar.gz && \ tar xvf azcopy_linux_amd64_10.17.0.tar.gz && \ mkdir -p ~/.local/bin && \ mv azcopy_linux_amd64_10.17.0/azcopy ~/.local/bin && \ chmod +x ~/.local/bin/azcopy && \ rm -rf azcopy_linux_amd64* # Setup conda RUN cd /tmp && \ wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh && \ bash ./Miniconda3-latest-Linux-x86_64.sh -b && \ rm ./Miniconda3-latest-Linux-x86_64.sh # Install dotnet RUN cd /tmp && \ wget https://dot.net/v1/dotnet-install.sh && \ chmod +x dotnet-install.sh && \ ./dotnet-install.sh --channel 7.0 && \ ./dotnet-install.sh --channel 3.1 && \ rm ./dotnet-install.sh ================================================ FILE: .devcontainer/devcontainer.env ================================================ SAMPLE_ENV_VAR1="Sample Value" SAMPLE_ENV_VAR2=332431bf-68bf ================================================ FILE: .devcontainer/devcontainer.json ================================================ { "name": "LLaVA", "build": { "dockerfile": "Dockerfile", "context": "..", "args": {} }, "features": { "ghcr.io/devcontainers/features/docker-in-docker:2": {}, "ghcr.io/devcontainers/features/azure-cli:1": {}, "ghcr.io/azure/azure-dev/azd:0": {}, "ghcr.io/devcontainers/features/powershell:1": {}, "ghcr.io/devcontainers/features/common-utils:2": {}, "ghcr.io/devcontainers-contrib/features/zsh-plugins:0": {}, }, // "forwardPorts": [], "postCreateCommand": "bash ./.devcontainer/postCreateCommand.sh", "customizations": { "vscode": { "settings": { "python.analysis.autoImportCompletions": true, "python.analysis.autoImportUserSymbols": true, "python.defaultInterpreterPath": "~/miniconda3/envs/llava/bin/python", "python.formatting.provider": "yapf", "python.linting.enabled": true, "python.linting.flake8Enabled": true, "isort.check": true, "dev.containers.copyGitConfig": true, "terminal.integrated.defaultProfile.linux": "zsh", "terminal.integrated.profiles.linux": { "zsh": { "path": "/usr/bin/zsh" }, } }, "extensions": [ "aaron-bond.better-comments", "eamodio.gitlens", "EditorConfig.EditorConfig", "foxundermoon.shell-format", "GitHub.copilot-chat", "GitHub.copilot-labs", "GitHub.copilot", "lehoanganh298.json-lines-viewer", "mhutchie.git-graph", "ms-azuretools.vscode-docker", "ms-dotnettools.dotnet-interactive-vscode", "ms-python.flake8", "ms-python.isort", "ms-python.python", "ms-python.vscode-pylance", "njpwerner.autodocstring", "redhat.vscode-yaml", "stkb.rewrap", "yzhang.markdown-all-in-one", ] } }, "mounts": [], "runArgs": [ "--gpus", "all", // "--ipc", // "host", "--ulimit", "memlock=-1", "--env-file", ".devcontainer/devcontainer.env" ], // "remoteUser": "root" } ================================================ FILE: .devcontainer/postCreateCommand.sh ================================================ git config --global safe.directory '*' git config --global core.editor "code --wait" git config --global pager.branch false # Set AZCOPY concurrency to auto echo "export AZCOPY_CONCURRENCY_VALUE=AUTO" >> ~/.zshrc echo "export AZCOPY_CONCURRENCY_VALUE=AUTO" >> ~/.bashrc # Activate conda by default echo ". /home/vscode/miniconda3/bin/activate" >> ~/.zshrc echo ". /home/vscode/miniconda3/bin/activate" >> ~/.bashrc # Use llava environment by default echo "conda activate llava" >> ~/.zshrc echo "conda activate llava" >> ~/.bashrc # Add dotnet to PATH echo 'export PATH="$PATH:$HOME/.dotnet"' >> ~/.bashrc echo 'export PATH="$PATH:$HOME/.dotnet"' >> ~/.zshrc # Create and activate llava environment source /home/vscode/miniconda3/bin/activate conda create -y -q -n llava python=3.10 conda activate llava # Install Nvidia Cuda Compiler conda install -y -c nvidia cuda-compiler pip install pre-commit==3.0.2 # Install package locally pip install --upgrade pip # enable PEP 660 support pip install -e . # Install additional packages for training pip install -e ".[train]" pip install flash-attn --no-build-isolation # Download checkpoints to location outside of the repo git clone https://huggingface.co/liuhaotian/llava-v1.5-7b ~/llava-v1.5-7b # Commented because it is unlikely for users to have enough local GPU memory to load the model # git clone https://huggingface.co/liuhaotian/llava-v1.5-13b ~/llava-v1.5-13b echo "postCreateCommand.sh COMPLETE!" ================================================ FILE: .dockerignore ================================================ # The .dockerignore file excludes files from the container build process. # # https://docs.docker.com/engine/reference/builder/#dockerignore-file # Exclude Git files .git .github .gitignore # Exclude Python cache files __pycache__ .mypy_cache .pytest_cache .ruff_cache # Exclude Python virtual environment /venv # Exclude some weights /openai /liuhaotian ================================================ FILE: .editorconfig ================================================ root = true # Unix-style newlines with a newline ending every file [*] end_of_line = lf insert_final_newline = true trim_trailing_whitespace = true charset = utf-8 # 4 space indentation [*.{py,json}] indent_style = space indent_size = 4 # 2 space indentation [*.{md,sh,yaml,yml}] indent_style = space indent_size = 2 ================================================ FILE: .gitattributes ================================================ # https://git-scm.com/docs/gitattributes # Set the default behavior, in case people don't have core.autocrlf set. # https://git-scm.com/docs/gitattributes#_end_of_line_conversion * text=auto # common python attributes, taken from https://github.com/alexkaratarakis/gitattributes/blob/710900479a2bedeec7003d381719521ffbb18bf8/Python.gitattributes # Source files # ============ *.pxd text diff=python *.py text diff=python *.py3 text diff=python *.pyw text diff=python *.pyx text diff=python *.pyz text diff=python *.pyi text diff=python # Binary files # ============ *.db binary *.p binary *.pkl binary *.pickle binary *.pyc binary export-ignore *.pyo binary export-ignore *.pyd binary # Jupyter notebook *.ipynb text eol=lf ================================================ FILE: .github/ISSUE_TEMPLATE/1-usage.yaml ================================================ name: Usage issues description: Report issues in usage. title: "[Usage] " body: - type: markdown attributes: value: | Thanks for taking the time to fill out this form. Please give as detailed description as possible for us to better assist with the issue :) - type: textarea id: what-happened attributes: label: Describe the issue description: Please give as detailed description as possible for us to better assist with the issue. Please paste the **FULL** error log here, so that we can better understand the issue. Wrap the log with ``` for better readability in GitHub. placeholder: Issue value: | Issue: Command: ``` PASTE THE COMMANDS HERE. ``` Log: ``` PASTE THE LOGS HERE. ``` Screenshots: You may attach screenshots if it better explains the issue. validations: required: true ================================================ FILE: .github/ISSUE_TEMPLATE/2-feature-request.yaml ================================================ name: Feature Request description: Request for a new feature title: "[Feature request] " body: - type: markdown attributes: value: | Thanks for your interest in our work. Please share your thoughts of the new features below. - type: textarea id: feature attributes: label: feature placeholder: Start your thoughts here... ================================================ FILE: .github/ISSUE_TEMPLATE/3-question.yaml ================================================ name: Questions description: General questions about the work title: "[Question] " body: - type: markdown attributes: value: | Thanks for your interest in our work. For this type of question, it may be more suitable to go to [discussion](https://github.com/haotian-liu/LLaVA/discussions) sections. If you believe an issue would be better for your request, please continue your post below :) - type: textarea id: question attributes: label: Question placeholder: Start question here... ================================================ FILE: .github/ISSUE_TEMPLATE/4-discussion.yaml ================================================ name: Discussions description: General discussions about the work title: "[Discussion] " body: - type: markdown attributes: value: | Thanks for your interest in our work. For this type of question, it may be more suitable to go to [discussion](https://github.com/haotian-liu/LLaVA/discussions) sections. If you believe an issue would be better for your request, please continue your post below :) - type: textarea id: discussion attributes: label: Discussion placeholder: Start discussion here... ================================================ FILE: .gitignore ================================================ # Python __pycache__ *.pyc *.egg-info dist # Log *.log *.log.* *.json *.jsonl # Data !**/alpaca-data-conversation.json # Editor .idea *.swp # Other .DS_Store wandb output checkpoints ckpts* .ipynb_checkpoints *.ipynb # DevContainer !.devcontainer/* # Demo serve_images/ ================================================ FILE: LICENSE ================================================ Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. ================================================ FILE: README.md ================================================ # 🌋 LLaVA: Large Language and Vision Assistant *Visual instruction tuning towards large language and vision models with GPT-4 level capabilities.* [📢 [LLaVA-NeXT Blog](https://llava-vl.github.io/blog/2024-01-30-llava-next/)] [[Project Page](https://llava-vl.github.io/)] [[Demo](https://llava.hliu.cc/)] [[Data](https://github.com/haotian-liu/LLaVA/blob/main/docs/Data.md)] [[Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)] 🤝Community Contributions: [[llama.cpp](https://github.com/ggerganov/llama.cpp/pull/3436)] [[Colab](https://github.com/camenduru/LLaVA-colab)] [[🤗Space](https://huggingface.co/spaces/badayvedat/LLaVA)] [[Replicate](https://replicate.com/yorickvp/llava-13b)] [[AutoGen](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_lmm_llava.ipynb)] [[BakLLaVA](https://github.com/SkunkworksAI/BakLLaVA)] **Improved Baselines with Visual Instruction Tuning** [[Paper](https://arxiv.org/abs/2310.03744)] [[HF](https://huggingface.co/papers/2310.03744)]
[Haotian Liu](https://hliu.cc), [Chunyuan Li](https://chunyuan.li/), [Yuheng Li](https://yuheng-li.github.io/), [Yong Jae Lee](https://pages.cs.wisc.edu/~yongjaelee/) **Visual Instruction Tuning** (NeurIPS 2023, **Oral**) [[Paper](https://arxiv.org/abs/2304.08485)] [[HF](https://huggingface.co/papers/2304.08485)]
[Haotian Liu*](https://hliu.cc), [Chunyuan Li*](https://chunyuan.li/), [Qingyang Wu](https://scholar.google.ca/citations?user=HDiw-TsAAAAJ&hl=en/), [Yong Jae Lee](https://pages.cs.wisc.edu/~yongjaelee/) (*Equal Contribution) ## Release - [2024/05/10] 🔥 **LLaVA-NeXT** (Stronger) models are released, stronger LMM with support of LLama-3 (8B) and Qwen-1.5 (72B/110B). [[Blog](https://llava-vl.github.io/blog/2024-05-10-llava-next-stronger-llms/)] [[Checkpoints](https://huggingface.co/collections/lmms-lab/llava-next-6623288e2d61edba3ddbf5ff)] [[Demo](https://llava-next.lmms-lab.com/)] [[Code](https://github.com/LLaVA-VL/LLaVA-NeXT/)] - [2024/05/10] 🔥 **LLaVA-NeXT** (Video) is released. The image-only-trained LLaVA-NeXT model is surprisingly strong on video tasks with zero-shot modality transfer. DPO training with AI feedback on videos can yield significant improvement. [[Blog](https://llava-vl.github.io/blog/2024-04-30-llava-next-video/)] [[Checkpoints](https://huggingface.co/collections/lmms-lab/llava-next-video-661e86f5e8dabc3ff793c944)] [[Code](https://github.com/LLaVA-VL/LLaVA-NeXT/)] - [03/10] Releasing **LMMs-Eval**, a highly efficient evaluation pipeline we used when developing LLaVA-NeXT. It supports the evaluation of LMMs on dozens of public datasets and allows new dataset onboarding, making the dev of new LMMs much faster. [[Blog](https://lmms-lab.github.io/lmms-eval-blog/lmms-eval-0.1/)] [[Codebase](https://github.com/EvolvingLMMs-Lab/lmms-eval)] - [1/30] 🔥 **LLaVA-NeXT** (LLaVA-1.6) is out! With additional scaling to LLaVA-1.5, LLaVA-NeXT-34B outperforms Gemini Pro on some benchmarks. It can now process 4x more pixels and perform more tasks/applications than before. Check out the [blog post](https://llava-vl.github.io/blog/2024-01-30-llava-next/), and explore the [demo](https://llava.hliu.cc/)! Models are available in [Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md). Training/eval data and scripts coming soon. - [11/10] [LLaVA-Plus](https://llava-vl.github.io/llava-plus/) is released: Learning to Use Tools for Creating Multimodal Agents, with LLaVA-Plus (LLaVA that Plug and Learn to Use Skills). [[Project Page](https://llava-vl.github.io/llava-plus/)] [[Demo](https://llavaplus.ngrok.io/)] [[Code](https://github.com/LLaVA-VL/LLaVA-Plus-Codebase)] [[Paper](https://arxiv.org/abs/2311.05437)] - [11/2] [LLaVA-Interactive](https://llava-vl.github.io/llava-interactive/) is released: Experience the future of human-AI multimodal interaction with an all-in-one demo for Image Chat, Segmentation, Generation and Editing. [[Project Page](https://llava-vl.github.io/llava-interactive/)] [[Demo](https://llavainteractive.ngrok.io/)] [[Code](https://github.com/LLaVA-VL/LLaVA-Interactive-Demo)] [[Paper](https://arxiv.org/abs/2311.00571)] - [10/26] 🔥 LLaVA-1.5 with LoRA achieves comparable performance as full-model finetuning, with a reduced GPU RAM requirement ([ckpts](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md#llava-v15), [script](https://github.com/haotian-liu/LLaVA#train)). We also provide a [doc](https://github.com/haotian-liu/LLaVA/blob/main/docs/Finetune_Custom_Data.md) on how to finetune LLaVA-1.5 on your own dataset with LoRA. - [10/12] Check out the Korean LLaVA (Ko-LLaVA), created by ETRI, who has generously supported our research! [[🤗 Demo](https://huggingface.co/spaces/etri-vilab/Ko-LLaVA)] - [10/5] 🔥 LLaVA-1.5 is out! Achieving SoTA on 11 benchmarks, with just simple modifications to the original LLaVA, utilizes all public data, completes training in ~1 day on a single 8-A100 node, and surpasses methods like Qwen-VL-Chat that use billion-scale data. Check out the [technical report](https://arxiv.org/abs/2310.03744), and explore the [demo](https://llava.hliu.cc/)! Models are available in [Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md). The training data and scripts of LLaVA-1.5 are released [here](https://github.com/haotian-liu/LLaVA#train), and evaluation scripts are released [here](https://github.com/haotian-liu/LLaVA/blob/main/docs/Evaluation.md)! - [9/26] LLaVA is improved with reinforcement learning from human feedback (RLHF) to improve fact grounding and reduce hallucination. Check out the new SFT and RLHF checkpoints at project [[LLavA-RLHF]](https://llava-rlhf.github.io/) - [9/22] [LLaVA](https://arxiv.org/abs/2304.08485) is accepted by NeurIPS 2023 as **oral presentation**, and [LLaVA-Med](https://arxiv.org/abs/2306.00890) is accepted by NeurIPS 2023 Datasets and Benchmarks Track as **spotlight presentation**.
More - [11/6] Support **Intel** dGPU and CPU platforms. [More details here.](https://github.com/haotian-liu/LLaVA/tree/intel/docs/intel) - [10/12] LLaVA is now supported in [llama.cpp](https://github.com/ggerganov/llama.cpp/pull/3436) with 4-bit / 5-bit quantization support! - [10/11] The training data and scripts of LLaVA-1.5 are released [here](https://github.com/haotian-liu/LLaVA#train), and evaluation scripts are released [here](https://github.com/haotian-liu/LLaVA/blob/main/docs/Evaluation.md)! - [10/10] [Roboflow Deep Dive](https://blog.roboflow.com/first-impressions-with-llava-1-5/): First Impressions with LLaVA-1.5. - [9/20] We summarize our empirical study of training 33B and 65B LLaVA models in a [note](https://arxiv.org/abs/2309.09958). Further, if you are interested in the comprehensive review, evolution and trend of multimodal foundation models, please check out our recent survey paper [``Multimodal Foundation Models: From Specialists to General-Purpose Assistants''.](https://arxiv.org/abs/2309.10020)

- [7/19] 🔥 We release a major upgrade, including support for LLaMA-2, LoRA training, 4-/8-bit inference, higher resolution (336x336), and a lot more. We release [LLaVA Bench](https://github.com/haotian-liu/LLaVA/blob/main/docs/LLaVA_Bench.md) for benchmarking open-ended visual chat with results from Bard and Bing-Chat. We also support and verify training with RTX 3090 and RTX A6000. Check out [LLaVA-from-LLaMA-2](https://github.com/haotian-liu/LLaVA/blob/main/docs/LLaVA_from_LLaMA2.md), and our [model zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)! - [6/26] [CVPR 2023 Tutorial](https://vlp-tutorial.github.io/) on **Large Multimodal Models: Towards Building and Surpassing Multimodal GPT-4**! Please check out [[Slides](https://datarelease.blob.core.windows.net/tutorial/vision_foundation_models_2023/slides/Chunyuan_cvpr2023_tutorial_lmm.pdf)] [[Notes](https://arxiv.org/abs/2306.14895)] [[YouTube](https://youtu.be/mkI7EPD1vp8)] [[Bilibli](https://www.bilibili.com/video/BV1Ng4y1T7v3/)]. - [6/11] We released the preview for the most requested feature: DeepSpeed and LoRA support! Please see documentations [here](./docs/LoRA.md). - [6/1] We released **LLaVA-Med: Large Language and Vision Assistant for Biomedicine**, a step towards building biomedical domain large language and vision models with GPT-4 level capabilities. Checkout the [paper](https://arxiv.org/abs/2306.00890) and [page](https://github.com/microsoft/LLaVA-Med). - [5/6] We are releasing [LLaVA-Lighting-MPT-7B-preview](https://huggingface.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview), based on MPT-7B-Chat! See [here](#LLaVA-MPT-7b) for more details. - [5/2] 🔥 We are releasing LLaVA-Lighting! Train a lite, multimodal GPT-4 with just $40 in 3 hours! See [here](#train-llava-lightning) for more details. - [4/27] Thanks to the community effort, LLaVA-13B with 4-bit quantization allows you to run on a GPU with as few as 12GB VRAM! Try it out [here](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/llava). - [4/17] 🔥 We released **LLaVA: Large Language and Vision Assistant**. We propose visual instruction tuning, towards building large language and vision models with GPT-4 level capabilities. Checkout the [paper](https://arxiv.org/abs/2304.08485) and [demo](https://llava.hliu.cc/).
[![Code License](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)](https://github.com/tatsu-lab/stanford_alpaca/blob/main/LICENSE) **Usage and License Notices**: This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses, including but not limited to the [OpenAI Terms of Use](https://openai.com/policies/terms-of-use) for the dataset and the specific licenses for base language models for checkpoints trained using the dataset (e.g. [Llama community license](https://ai.meta.com/llama/license/) for LLaMA-2 and Vicuna-v1.5). This project does not impose any additional constraints beyond those stipulated in the original licenses. Furthermore, users are reminded to ensure that their use of the dataset and checkpoints is in compliance with all applicable laws and regulations. ## Contents - [Install](#install) - [LLaVA Weights](#llava-weights) - [Demo](#Demo) - [Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md) - [Dataset](https://github.com/haotian-liu/LLaVA/blob/main/docs/Data.md) - [Train](#train) - [Evaluation](#evaluation) ## Install If you are not using Linux, do *NOT* proceed, see instructions for [macOS](https://github.com/haotian-liu/LLaVA/blob/main/docs/macOS.md) and [Windows](https://github.com/haotian-liu/LLaVA/blob/main/docs/Windows.md). 1. Clone this repository and navigate to LLaVA folder ```bash git clone https://github.com/haotian-liu/LLaVA.git cd LLaVA ``` 2. Install Package ```Shell conda create -n llava python=3.10 -y conda activate llava pip install --upgrade pip # enable PEP 660 support pip install -e . ``` 3. Install additional packages for training cases ``` pip install -e ".[train]" pip install flash-attn --no-build-isolation ``` ### Upgrade to latest code base ```Shell git pull pip install -e . # if you see some import errors when you upgrade, # please try running the command below (without #) # pip install flash-attn --no-build-isolation --no-cache-dir ``` ### Quick Start With HuggingFace
Example Code ```Python from llava.model.builder import load_pretrained_model from llava.mm_utils import get_model_name_from_path from llava.eval.run_llava import eval_model model_path = "liuhaotian/llava-v1.5-7b" tokenizer, model, image_processor, context_len = load_pretrained_model( model_path=model_path, model_base=None, model_name=get_model_name_from_path(model_path) ) ``` Check out the details wth the `load_pretrained_model` function in `llava/model/builder.py`. You can also use the `eval_model` function in `llava/eval/run_llava.py` to get the output easily. By doing so, you can use this code on Colab directly after downloading this repository. ``` python model_path = "liuhaotian/llava-v1.5-7b" prompt = "What are the things I should be cautious about when I visit here?" image_file = "https://llava-vl.github.io/static/images/view.jpg" args = type('Args', (), { "model_path": model_path, "model_base": None, "model_name": get_model_name_from_path(model_path), "query": prompt, "conv_mode": None, "image_file": image_file, "sep": ",", "temperature": 0, "top_p": None, "num_beams": 1, "max_new_tokens": 512 })() eval_model(args) ```
## LLaVA Weights Please check out our [Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md) for all public LLaVA checkpoints, and the instructions of how to use the weights. ## Demo ### Gradio Web UI To launch a Gradio demo locally, please run the following commands one by one. If you plan to launch multiple model workers to compare between different checkpoints, you only need to launch the controller and the web server *ONCE*. ```mermaid flowchart BT %% Declare Nodes gws("Gradio (UI Server)") c("Controller (API Server):
PORT: 10000") mw7b("Model Worker:
llava-v1.5-7b
PORT: 40000") mw13b("Model Worker:
llava-v1.5-13b
PORT: 40001") sglw13b("SGLang Backend:
llava-v1.6-34b
http://localhost:30000") lsglw13b("SGLang Worker:
llava-v1.6-34b
PORT: 40002") %% Declare Styles classDef data fill:#3af,stroke:#48a,stroke-width:2px,color:#444 classDef success fill:#8f8,stroke:#0a0,stroke-width:2px,color:#444 classDef failure fill:#f88,stroke:#f00,stroke-width:2px,color:#444 %% Assign Styles class id,od data; class cimg,cs_s,scsim_s success; class ncimg,cs_f,scsim_f failure; subgraph Demo Connections direction BT c<-->gws mw7b<-->c mw13b<-->c lsglw13b<-->c sglw13b<-->lsglw13b end ``` #### Launch a controller ```Shell python -m llava.serve.controller --host 0.0.0.0 --port 10000 ``` #### Launch a gradio web server. ```Shell python -m llava.serve.gradio_web_server --controller http://localhost:10000 --model-list-mode reload ``` You just launched the Gradio web interface. Now, you can open the web interface with the URL printed on the screen. You may notice that there is no model in the model list. Do not worry, as we have not launched any model worker yet. It will be automatically updated when you launch a model worker. #### Launch a SGLang worker This is the recommended way to serve LLaVA model with high throughput, and you need to install SGLang first. Note that currently `4-bit` quantization is not supported yet on SGLang-LLaVA, and if you have limited GPU VRAM, please check out model worker with [quantization](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#launch-a-model-worker-4-bit-8-bit-inference-quantized). ```Shell pip install "sglang[all]" ``` You'll first launch a SGLang backend worker which will execute the models on GPUs. Remember the `--port` you've set and you'll use that later. ```Shell # Single GPU CUDA_VISIBLE_DEVICES=0 python3 -m sglang.launch_server --model-path liuhaotian/llava-v1.5-7b --tokenizer-path llava-hf/llava-1.5-7b-hf --port 30000 # Multiple GPUs with tensor parallel CUDA_VISIBLE_DEVICES=0,1 python3 -m sglang.launch_server --model-path liuhaotian/llava-v1.5-13b --tokenizer-path llava-hf/llava-1.5-13b-hf --port 30000 --tp 2 ``` Tokenizers (temporary): `llava-hf/llava-1.5-7b-hf`, `llava-hf/llava-1.5-13b-hf`, `liuhaotian/llava-v1.6-34b-tokenizer`. You'll then launch a LLaVA-SGLang worker that will communicate between LLaVA controller and SGLang backend to route the requests. Set `--sgl-endpoint` to `http://127.0.0.1:port` where `port` is the one you just set (default: 30000). ```Shell python -m llava.serve.sglang_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --sgl-endpoint http://127.0.0.1:30000 ``` #### Launch a model worker This is the actual *worker* that performs the inference on the GPU. Each worker is responsible for a single model specified in `--model-path`. ```Shell python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path liuhaotian/llava-v1.5-13b ``` Wait until the process finishes loading the model and you see "Uvicorn running on ...". Now, refresh your Gradio web UI, and you will see the model you just launched in the model list. You can launch as many workers as you want, and compare between different model checkpoints in the same Gradio interface. Please keep the `--controller` the same, and modify the `--port` and `--worker` to a different port number for each worker. ```Shell python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port --worker http://localhost: --model-path ``` If you are using an Apple device with an M1 or M2 chip, you can specify the mps device by using the `--device` flag: `--device mps`. #### Launch a model worker (Multiple GPUs, when GPU VRAM <= 24GB) If the VRAM of your GPU is less than 24GB (e.g., RTX 3090, RTX 4090, etc.), you may try running it with multiple GPUs. Our latest code base will automatically try to use multiple GPUs if you have more than one GPU. You can specify which GPUs to use with `CUDA_VISIBLE_DEVICES`. Below is an example of running with the first two GPUs. ```Shell CUDA_VISIBLE_DEVICES=0,1 python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path liuhaotian/llava-v1.5-13b ``` #### Launch a model worker (4-bit, 8-bit inference, quantized) You can launch the model worker with quantized bits (4-bit, 8-bit), which allows you to run the inference with reduced GPU memory footprint, potentially allowing you to run on a GPU with as few as 12GB VRAM. Note that inference with quantized bits may not be as accurate as the full-precision model. Simply append `--load-4bit` or `--load-8bit` to the **model worker** command that you are executing. Below is an example of running with 4-bit quantization. ```Shell python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path liuhaotian/llava-v1.5-13b --load-4bit ``` #### Launch a model worker (LoRA weights, unmerged) You can launch the model worker with LoRA weights, without merging them with the base checkpoint, to save disk space. There will be additional loading time, while the inference speed is the same as the merged checkpoints. Unmerged LoRA checkpoints do not have `lora-merge` in the model name, and are usually much smaller (less than 1GB) than the merged checkpoints (13G for 7B, and 25G for 13B). To load unmerged LoRA weights, you simply need to pass an additional argument `--model-base`, which is the base LLM that is used to train the LoRA weights. You can check the base LLM of each LoRA weights in the [model zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md). ```Shell python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path liuhaotian/llava-v1-0719-336px-lora-vicuna-13b-v1.3 --model-base lmsys/vicuna-13b-v1.3 ``` ### CLI Inference Chat about images using LLaVA without the need of Gradio interface. It also supports multiple GPUs, 4-bit and 8-bit quantized inference. With 4-bit quantization, for our LLaVA-1.5-7B, it uses less than 8GB VRAM on a single GPU. ```Shell python -m llava.serve.cli \ --model-path liuhaotian/llava-v1.5-7b \ --image-file "https://llava-vl.github.io/static/images/view.jpg" \ --load-4bit ``` ## Train *Below is the latest training configuration for LLaVA v1.5. For legacy models, please refer to README of [this](https://github.com/haotian-liu/LLaVA/tree/v1.0.1) version for now. We'll add them in a separate doc later.* LLaVA training consists of two stages: (1) feature alignment stage: use our 558K subset of the LAION-CC-SBU dataset to connect a *frozen pretrained* vision encoder to a *frozen LLM*; (2) visual instruction tuning stage: use 150K GPT-generated multimodal instruction-following data, plus around 515K VQA data from academic-oriented tasks, to teach the model to follow multimodal instructions. LLaVA is trained on 8 A100 GPUs with 80GB memory. To train on fewer GPUs, you can reduce the `per_device_train_batch_size` and increase the `gradient_accumulation_steps` accordingly. Always keep the global batch size the same: `per_device_train_batch_size` x `gradient_accumulation_steps` x `num_gpus`. ### Hyperparameters We use a similar set of hyperparameters as Vicuna in finetuning. Both hyperparameters used in pretraining and finetuning are provided below. 1. Pretraining | Hyperparameter | Global Batch Size | Learning rate | Epochs | Max length | Weight decay | | --- | ---: | ---: | ---: | ---: | ---: | | LLaVA-v1.5-13B | 256 | 1e-3 | 1 | 2048 | 0 | 2. Finetuning | Hyperparameter | Global Batch Size | Learning rate | Epochs | Max length | Weight decay | | --- | ---: | ---: | ---: | ---: | ---: | | LLaVA-v1.5-13B | 128 | 2e-5 | 1 | 2048 | 0 | ### Download Vicuna checkpoints (automatically) Our base model Vicuna v1.5, which is an instruction-tuned chatbot, will be downloaded automatically when you run our provided training scripts. No action is needed. ### Pretrain (feature alignment) Please download the 558K subset of the LAION-CC-SBU dataset with BLIP captions we use in the paper [here](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain). Pretrain takes around 5.5 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 3.5 hours for LLaVA-v1.5-7B. Training script with DeepSpeed ZeRO-2: [`pretrain.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/pretrain.sh). - `--mm_projector_type mlp2x_gelu`: the two-layer MLP vision-language connector. - `--vision_tower openai/clip-vit-large-patch14-336`: CLIP ViT-L/14 336px.
Pretrain takes around 20 hours for LLaVA-7B on 8x V100 (32G) We provide training script with DeepSpeed [here](https://github.com/haotian-liu/LLaVA/blob/main/scripts/pretrain_xformers.sh). Tips: - If you are using V100 which is not supported by FlashAttention, you can use the [memory-efficient attention](https://arxiv.org/abs/2112.05682) implemented in [xFormers](https://github.com/facebookresearch/xformers). Install xformers and replace `llava/train/train_mem.py` above with [llava/train/train_xformers.py](llava/train/train_xformers.py).
### Visual Instruction Tuning 1. Prepare data Please download the annotation of the final mixture our instruction tuning data [llava_v1_5_mix665k.json](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/llava_v1_5_mix665k.json), and download the images from constituting datasets: - COCO: [train2017](http://images.cocodataset.org/zips/train2017.zip) - GQA: [images](https://downloads.cs.stanford.edu/nlp/data/gqa/images.zip) - OCR-VQA: [download script](https://drive.google.com/drive/folders/1_GYPY5UkUy7HIcR0zq3ZCFgeZN7BAfm_?usp=sharing), **we save all files as `.jpg`** - TextVQA: [train_val_images](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip) - VisualGenome: [part1](https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip), [part2](https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip) After downloading all of them, organize the data as follows in `./playground/data`, ``` ├── coco │ └── train2017 ├── gqa │ └── images ├── ocr_vqa │ └── images ├── textvqa │ └── train_images └── vg ├── VG_100K └── VG_100K_2 ``` 2. Start training! You may download our pretrained projectors in [Model Zoo](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md). It is not recommended to use legacy projectors, as they may be trained with a different version of the codebase, and if any option is off, the model will not function/train as we expected. Visual instruction tuning takes around 20 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 10 hours for LLaVA-v1.5-7B on 8x A100 (40G). Training script with DeepSpeed ZeRO-3: [`finetune.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/finetune.sh). If you are do not have enough GPU memory: - Use LoRA: [`finetune_lora.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/finetune_lora.sh). We are able to fit 13B training in 8-A100-40G/8-A6000, and 7B training in 8-RTX3090. Make sure `per_device_train_batch_size*gradient_accumulation_steps` is the same as the provided script for best reproducibility. - Replace `zero3.json` with `zero3_offload.json` which offloads some parameters to CPU RAM. This slows down the training speed. If you are interested in finetuning LLaVA model to your own task/data, please check out [`Finetune_Custom_Data.md`](https://github.com/haotian-liu/LLaVA/blob/main/docs/Finetune_Custom_Data.md)。 New options to note: - `--mm_projector_type mlp2x_gelu`: the two-layer MLP vision-language connector. - `--vision_tower openai/clip-vit-large-patch14-336`: CLIP ViT-L/14 336px. - `--image_aspect_ratio pad`: this pads the non-square images to square, instead of cropping them; it slightly reduces hallucination. - `--group_by_modality_length True`: this should only be used when your instruction tuning dataset contains both language (e.g. ShareGPT) and multimodal (e.g. LLaVA-Instruct). It makes the training sampler only sample a single modality (either image or language) during training, which we observe to speed up training by ~25%, and does not affect the final outcome. ## Evaluation In LLaVA-1.5, we evaluate models on a diverse set of 12 benchmarks. To ensure the reproducibility, we evaluate the models with greedy decoding. We do not evaluate using beam search to make the inference process consistent with the chat demo of real-time outputs. See [Evaluation.md](https://github.com/haotian-liu/LLaVA/blob/main/docs/Evaluation.md). ### GPT-assisted Evaluation Our GPT-assisted evaluation pipeline for multimodal modeling is provided for a comprehensive understanding of the capabilities of vision-language models. Please see our paper for more details. 1. Generate LLaVA responses ```Shell python model_vqa.py \ --model-path ./checkpoints/LLaVA-13B-v0 \ --question-file \ playground/data/coco2014_val_qa_eval/qa90_questions.jsonl \ --image-folder \ /path/to/coco2014_val \ --answers-file \ /path/to/answer-file-our.jsonl ``` 2. Evaluate the generated responses. In our case, [`answer-file-ref.jsonl`](./playground/data/coco2014_val_qa_eval/qa90_gpt4_answer.jsonl) is the response generated by text-only GPT-4 (0314), with the context captions/boxes provided. ```Shell OPENAI_API_KEY="sk-***********************************" python llava/eval/eval_gpt_review_visual.py \ --question playground/data/coco2014_val_qa_eval/qa90_questions.jsonl \ --context llava/eval/table/caps_boxes_coco2014_val_80.jsonl \ --answer-list \ /path/to/answer-file-ref.jsonl \ /path/to/answer-file-our.jsonl \ --rule llava/eval/table/rule.json \ --output /path/to/review.json ``` 3. Summarize the evaluation results ```Shell python summarize_gpt_review.py ``` ## Citation If you find LLaVA useful for your research and applications, please cite using this BibTeX: ```bibtex @misc{liu2024llavanext, title={LLaVA-NeXT: Improved reasoning, OCR, and world knowledge}, url={https://llava-vl.github.io/blog/2024-01-30-llava-next/}, author={Liu, Haotian and Li, Chunyuan and Li, Yuheng and Li, Bo and Zhang, Yuanhan and Shen, Sheng and Lee, Yong Jae}, month={January}, year={2024} } @misc{liu2023improvedllava, title={Improved Baselines with Visual Instruction Tuning}, author={Liu, Haotian and Li, Chunyuan and Li, Yuheng and Lee, Yong Jae}, publisher={arXiv:2310.03744}, year={2023}, } @misc{liu2023llava, title={Visual Instruction Tuning}, author={Liu, Haotian and Li, Chunyuan and Wu, Qingyang and Lee, Yong Jae}, publisher={NeurIPS}, year={2023}, } ``` ## Acknowledgement - [Vicuna](https://github.com/lm-sys/FastChat): the codebase we built upon, and our base model Vicuna-13B that has the amazing language capabilities! ## Related Projects - [Instruction Tuning with GPT-4](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) - [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://github.com/microsoft/LLaVA-Med) - [Otter: In-Context Multi-Modal Instruction Tuning](https://github.com/Luodian/Otter) For future project ideas, please check out: - [SEEM: Segment Everything Everywhere All at Once](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once) - [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything) to detect, segment, and generate anything by marrying [Grounding DINO](https://github.com/IDEA-Research/GroundingDINO) and [Segment-Anything](https://github.com/facebookresearch/segment-anything). ================================================ FILE: cog.yaml ================================================ # Configuration for Cog ⚙️ # Reference: https://github.com/replicate/cog/blob/main/docs/yaml.md build: gpu: true python_version: "3.11" python_packages: - "torch==2.0.1" - "accelerate==0.21.0" - "bitsandbytes==0.41.0" - "deepspeed==0.9.5" - "einops-exts==0.0.4" - "einops==0.6.1" - "gradio==3.35.2" - "gradio_client==0.2.9" - "httpx==0.24.0" - "markdown2==2.4.10" - "numpy==1.26.0" - "peft==0.4.0" - "scikit-learn==1.2.2" - "sentencepiece==0.1.99" - "shortuuid==1.0.11" - "timm==0.6.13" - "tokenizers==0.13.3" - "torch==2.0.1" - "torchvision==0.15.2" - "transformers==4.31.0" - "wandb==0.15.12" - "wavedrom==2.0.3.post3" - "Pygments==2.16.1" run: - curl -o /usr/local/bin/pget -L "https://github.com/replicate/pget/releases/download/v0.0.3/pget" && chmod +x /usr/local/bin/pget # predict.py defines how predictions are run on your model predict: "predict.py:Predictor" ================================================ FILE: docs/Customize_Component.md ================================================ # Customize Components in LLaVA This is an initial guide on how to replace the LLMs, visual encoders, etc. with your choice of components. ## LLM It is quite simple to swap out LLaMA to any other LLMs. You can refer to our implementation of [`llava_llama.py`](https://raw.githubusercontent.com/haotian-liu/LLaVA/main/llava/model/language_model/llava_llama.py) for an example of how to replace the LLM. Although it may seem that it still needs ~100 lines of code, most of them are copied from the original `llama.py` from HF. The only part that is different is to insert some lines for processing the multimodal inputs. In `forward` function, you can see that we call `self.prepare_inputs_labels_for_multimodal` to process the multimodal inputs. This function is defined in `LlavaMetaForCausalLM` and you just need to insert it into the `forward` function of your LLM. In `prepare_inputs_for_generation` function, you can see that we add `images` to the `model_inputs`. This is because we need to pass the images to the LLM during generation. These are basically all the changes you need to make to replace the LLM. ## Visual Encoder You can check out [`clip_encoder.py`](https://github.com/haotian-liu/LLaVA/blob/main/llava/model/multimodal_encoder/clip_encoder.py) on how we implement the CLIP visual encoder. ================================================ FILE: docs/Data.md ================================================ ## Data | Data file name | Size | | --- | ---: | | [llava_instruct_150k.json](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/llava_instruct_150k.json) | 229 MB | | [llava_instruct_80k.json](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/llava_instruct_80k.json) | 229 MB | | [conversation_58k.json](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/conversation_58k.json) | 126 MB | | [detail_23k.json](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/detail_23k.json) | 20.5 MB | | [complex_reasoning_77k.json](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/complex_reasoning_77k.json) | 79.6 MB | ### Pretraining Dataset The pretraining dataset used in this release is a subset of CC-3M dataset, filtered with a more balanced concept coverage distribution. Please see [here](https://huggingface.co/datasets/liuhaotian/LLaVA-CC3M-Pretrain-595K) for a detailed description of the dataset structure and how to download the images. If you already have CC-3M dataset on your disk, the image names follow this format: `GCC_train_000000000.jpg`. You may edit the `image` field correspondingly if necessary. | Data | Chat File | Meta Data | Size | | --- | --- | --- | ---: | | CC-3M Concept-balanced 595K | [chat.json](https://huggingface.co/datasets/liuhaotian/LLaVA-CC3M-Pretrain-595K/blob/main/chat.json) | [metadata.json](https://huggingface.co/datasets/liuhaotian/LLaVA-CC3M-Pretrain-595K/blob/main/metadata.json) | 211 MB | LAION/CC/SBU BLIP-Caption Concept-balanced 558K | [blip_laion_cc_sbu_558k.json](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain/blob/main/blip_laion_cc_sbu_558k.json) | [metadata.json](#) | 181 MB **Important notice**: Upon the request from the community, as ~15% images of the original CC-3M dataset are no longer accessible, we upload [`images.zip`](https://huggingface.co/datasets/liuhaotian/LLaVA-CC3M-Pretrain-595K/blob/main/images.zip) for better reproducing our work in research community. It must not be used for any other purposes. The use of these images must comply with the CC-3M license. This may be taken down at any time when requested by the original CC-3M dataset owner or owners of the referenced images. ### GPT-4 Prompts We provide our prompts and few-shot samples for GPT-4 queries, to better facilitate research in this domain. Please check out the [`prompts`](https://github.com/haotian-liu/LLaVA/tree/main/playground/data/prompts) folder for three kinds of questions: conversation, detail description, and complex reasoning. They are organized in a format of `system_message.txt` for system message, pairs of `abc_caps.txt` for few-shot sample user input, and `abc_conv.txt` for few-shot sample reference output. Note that you may find them in different format. For example, `conversation` is in `jsonl`, and detail description is answer-only. The selected format in our preliminary experiments works slightly better than a limited set of alternatives that we tried: `jsonl`, more natural format, answer-only. If interested, you may try other variants or conduct more careful study in this. Contributions are welcomed! ================================================ FILE: docs/Evaluation.md ================================================ # Evaluation In LLaVA-1.5, we evaluate models on a diverse set of 12 benchmarks. To ensure the reproducibility, we evaluate the models with greedy decoding. We do not evaluate using beam search to make the inference process consistent with the chat demo of real-time outputs. Currently, we mostly utilize the official toolkit or server for the evaluation. ## Evaluate on Custom Datasets You can evaluate LLaVA on your custom datasets by converting your dataset to LLaVA's jsonl format, and evaluate using [`model_vqa.py`](https://github.com/haotian-liu/LLaVA/blob/main/llava/eval/model_vqa.py). Below we provide a general guideline for evaluating datasets with some common formats. 1. Short-answer (e.g. VQAv2, MME). ``` Answer the question using a single word or phrase. ``` 2. Option-only for multiple-choice (e.g. MMBench, SEED-Bench). ``` A. B. C. D. Answer with the option's letter from the given choices directly. ``` 3. Natural QA (e.g. LLaVA-Bench, MM-Vet). No postprocessing is needed. ## Scripts Before preparing task-specific data, **you MUST first download [eval.zip](https://drive.google.com/file/d/1atZSBBrAX54yYpxtVVW33zFvcnaHeFPy/view?usp=sharing)**. It contains custom annotations, scripts, and the prediction files with LLaVA v1.5. Extract to `./playground/data/eval`. This also provides a general structure for all datasets. ### VQAv2 1. Download [`test2015`](http://images.cocodataset.org/zips/test2015.zip) and put it under `./playground/data/eval/vqav2`. 2. Multi-GPU inference. ```Shell CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash scripts/v1_5/eval/vqav2.sh ``` 3. Submit the results to the [evaluation server](https://eval.ai/web/challenges/challenge-page/830/my-submission): `./playground/data/eval/vqav2/answers_upload`. ### GQA 1. Download the [data](https://cs.stanford.edu/people/dorarad/gqa/download.html) and [evaluation scripts](https://cs.stanford.edu/people/dorarad/gqa/evaluate.html) following the official instructions and put under `./playground/data/eval/gqa/data`. You may need to modify `eval.py` as [this](https://gist.github.com/haotian-liu/db6eddc2a984b4cbcc8a7f26fd523187) due to the missing assets in the GQA v1.2 release. 2. Multi-GPU inference. ```Shell CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash scripts/v1_5/eval/gqa.sh ``` ### VisWiz 1. Download [`test.json`](https://vizwiz.cs.colorado.edu/VizWiz_final/vqa_data/Annotations.zip) and extract [`test.zip`](https://vizwiz.cs.colorado.edu/VizWiz_final/images/test.zip) to `test`. Put them under `./playground/data/eval/vizwiz`. 2. Single-GPU inference. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/vizwiz.sh ``` 3. Submit the results to the [evaluation server](https://eval.ai/web/challenges/challenge-page/2185/my-submission): `./playground/data/eval/vizwiz/answers_upload`. ### ScienceQA 1. Under `./playground/data/eval/scienceqa`, download `images`, `pid_splits.json`, `problems.json` from the `data/scienceqa` folder of the ScienceQA [repo](https://github.com/lupantech/ScienceQA). 2. Single-GPU inference and evaluate. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/sqa.sh ``` ### TextVQA 1. Download [`TextVQA_0.5.1_val.json`](https://dl.fbaipublicfiles.com/textvqa/data/TextVQA_0.5.1_val.json) and [images](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip) and extract to `./playground/data/eval/textvqa`. 2. Single-GPU inference and evaluate. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/textvqa.sh ``` ### POPE 1. Download `coco` from [POPE](https://github.com/AoiDragon/POPE/tree/e3e39262c85a6a83f26cf5094022a782cb0df58d/output/coco) and put under `./playground/data/eval/pope`. 2. Single-GPU inference and evaluate. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/pope.sh ``` ### MME 1. Download the data following the official instructions [here](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation). 2. Downloaded images to `MME_Benchmark_release_version`. 3. put the official `eval_tool` and `MME_Benchmark_release_version` under `./playground/data/eval/MME`. 4. Single-GPU inference and evaluate. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/mme.sh ``` ### MMBench 1. Download [`mmbench_dev_20230712.tsv`](https://download.openmmlab.com/mmclassification/datasets/mmbench/mmbench_dev_20230712.tsv) and put under `./playground/data/eval/mmbench`. 2. Single-GPU inference. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/mmbench.sh ``` 3. Submit the results to the [evaluation server](https://opencompass.org.cn/leaderboard-multimodal): `./playground/data/eval/mmbench/answers_upload/mmbench_dev_20230712`. ### MMBench-CN 1. Download [`mmbench_dev_cn_20231003.tsv`](https://download.openmmlab.com/mmclassification/datasets/mmbench/mmbench_dev_cn_20231003.tsv) and put under `./playground/data/eval/mmbench`. 2. Single-GPU inference. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/mmbench_cn.sh ``` 3. Submit the results to the evaluation server: `./playground/data/eval/mmbench/answers_upload/mmbench_dev_cn_20231003`. ### SEED-Bench 1. Following the official [instructions](https://github.com/AILab-CVC/SEED-Bench/blob/main/DATASET.md) to download the images and the videos. Put images under `./playground/data/eval/seed_bench/SEED-Bench-image`. 2. Extract the video frame in the middle from the downloaded videos, and put them under `./playground/data/eval/seed_bench/SEED-Bench-video-image`. We provide our script `extract_video_frames.py` modified from the official one. 3. Multiple-GPU inference and evaluate. ```Shell CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash scripts/v1_5/eval/seed.sh ``` 4. Optionally, submit the results to the leaderboard: `./playground/data/eval/seed_bench/answers_upload` using the official jupyter notebook. ### LLaVA-Bench-in-the-Wild 1. Extract contents of [`llava-bench-in-the-wild`](https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild) to `./playground/data/eval/llava-bench-in-the-wild`. 2. Single-GPU inference and evaluate. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/llavabench.sh ``` ### MM-Vet 1. Extract [`mm-vet.zip`](https://github.com/yuweihao/MM-Vet/releases/download/v1/mm-vet.zip) to `./playground/data/eval/mmvet`. 2. Single-GPU inference. ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/mmvet.sh ``` 3. Evaluate the predictions in `./playground/data/eval/mmvet/results` using the official jupyter notebook. ## More Benchmarks Below are awesome benchmarks for multimodal understanding from the research community, that are not initially included in the LLaVA-1.5 release. ### Q-Bench 1. Download [`llvisionqa_dev.json`](https://huggingface.co/datasets/nanyangtu/LLVisionQA-QBench/resolve/main/llvisionqa_dev.json) (for `dev`-subset) and [`llvisionqa_test.json`](https://huggingface.co/datasets/nanyangtu/LLVisionQA-QBench/resolve/main/llvisionqa_test.json) (for `test`-subset). Put them under `./playground/data/eval/qbench`. 2. Download and extract [images](https://huggingface.co/datasets/nanyangtu/LLVisionQA-QBench/resolve/main/images_llvisionqa.tar) and put all the images directly under `./playground/data/eval/qbench/images_llviqionqa`. 3. Single-GPU inference (change `dev` to `test` for evaluation on test set). ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/qbench.sh dev ``` 4. Submit the results by instruction [here](https://github.com/VQAssessment/Q-Bench#option-1-submit-results): `./playground/data/eval/qbench/llvisionqa_dev_answers.jsonl`. ### Chinese-Q-Bench 1. Download [`质衡-问答-验证集.json`](https://huggingface.co/datasets/nanyangtu/LLVisionQA-QBench/resolve/main/%E8%B4%A8%E8%A1%A1-%E9%97%AE%E7%AD%94-%E9%AA%8C%E8%AF%81%E9%9B%86.json) (for `dev`-subset) and [`质衡-问答-测试集.json`](https://huggingface.co/datasets/nanyangtu/LLVisionQA-QBench/resolve/main/%E8%B4%A8%E8%A1%A1-%E9%97%AE%E7%AD%94-%E6%B5%8B%E8%AF%95%E9%9B%86.json) (for `test`-subset). Put them under `./playground/data/eval/qbench`. 2. Download and extract [images](https://huggingface.co/datasets/nanyangtu/LLVisionQA-QBench/resolve/main/images_llvisionqa.tar) and put all the images directly under `./playground/data/eval/qbench/images_llviqionqa`. 3. Single-GPU inference (change `dev` to `test` for evaluation on test set). ```Shell CUDA_VISIBLE_DEVICES=0 bash scripts/v1_5/eval/qbench_zh.sh dev ``` 4. Submit the results by instruction [here](https://github.com/VQAssessment/Q-Bench#option-1-submit-results): `./playground/data/eval/qbench/llvisionqa_zh_dev_answers.jsonl`. ================================================ FILE: docs/Finetune_Custom_Data.md ================================================ # Finetune LLaVA on Custom Datasets ## Dataset Format Convert your data to a JSON file of a List of all samples. Sample metadata should contain `id` (a unique identifier), `image` (the path to the image), and `conversations` (the conversation data between human and AI). A sample JSON for finetuning LLaVA for generating tag-style captions for Stable Diffusion: ```json [ { "id": "997bb945-628d-4724-b370-b84de974a19f", "image": "part-000001/997bb945-628d-4724-b370-b84de974a19f.jpg", "conversations": [ { "from": "human", "value": "\nWrite a prompt for Stable Diffusion to generate this image." }, { "from": "gpt", "value": "a beautiful painting of chernobyl by nekro, pascal blanche, john harris, greg rutkowski, sin jong hun, moebius, simon stalenhag. in style of cg art. ray tracing. cel shading. hyper detailed. realistic. ue 5. maya. octane render. " }, ] }, ... ] ``` ## Command If you have a limited task-specific data, we recommend finetuning from LLaVA checkpoints with LoRA following this [script](https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/finetune_task_lora.sh). If the amount of the task-specific data is sufficient, you can also finetune from LLaVA checkpoints with full-model finetuning following this [script](https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/finetune_task.sh). You may need to adjust the hyperparameters to fit each specific dataset and your hardware constraint. ================================================ FILE: docs/Intel.md ================================================ # Intel Platforms * Support [Intel GPU Max Series](https://www.intel.com/content/www/us/en/products/details/discrete-gpus/data-center-gpu/max-series.html) * Support [Intel CPU Sapphire Rapides](https://ark.intel.com/content/www/us/en/ark/products/codename/126212/products-formerly-sapphire-rapids.html) * Based on [Intel Extension for Pytorch](https://intel.github.io/intel-extension-for-pytorch) More details in [**intel branch**](https://github.com/haotian-liu/LLaVA/tree/intel/docs/intel) ================================================ FILE: docs/LLaVA_Bench.md ================================================ # LLaVA-Bench [[Download](https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild)] **-Introduction-** Large commercial multimodal chatbots have been released in this week, including - [Multimodal Bing-Chat by Microsoft](https://blogs.bing.com/search/july-2023/Bing-Chat-Enterprise-announced,-multimodal-Visual-Search-rolling-out-to-Bing-Chat) (July 18, 2023) - [Multimodal Bard by Google](https://bard.google.com/). These chatbots are presumably supported by proprietary large multimodal models (LMM). Compared with the open-source LMM such as LLaVA, proprietary LMM represent the scaling success upperbound of the current SoTA techniques. They share the goal of developing multimodal chatbots that follow human intents to complete various daily-life visual tasks in the wild. While it remains less explored how to evaluate multimodal chat ability, it provides useful feedback to study open-source LMMs against the commercial multimodal chatbots. In addition to the *LLaVA-Bench (COCO)* dataset we used to develop the early versions of LLaVA, we are releasing [*LLaVA-Bench (In-the-Wild)*](https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild) to the community for the public use. ## LLaVA-Bench (In-the-Wild *[Ongoing work]*) To evaluate the model's capability in more challenging tasks and generalizability to novel domains, we collect a diverse set of 24 images with 60 questions in total, including indoor and outdoor scenes, memes, paintings, sketches, etc, and associate each image with a highly-detailed and manually-curated description and a proper selection of questions. Such design also assesses the model's robustness to different prompts. In this release, we also categorize questions into three categories: conversation (simple QA), detailed description, and complex reasoning. We continue to expand and improve the diversity of the LLaVA-Bench (In-the-Wild). We manually query Bing-Chat and Bard to get the responses. ### Results The score is measured by comparing against a reference answer generated by text-only GPT-4. It is generated by feeding the question, along with the ground truth image annotations as the context. A text-only GPT-4 evaluator rates both answers. We query GPT-4 by putting the reference answer first, and then the answer generated by the candidate model. We upload images at their original resolution to Bard and Bing-Chat to obtain the results. | Approach | Conversation | Detail | Reasoning | Overall | |----------------|--------------|--------|-----------|---------| | Bard-0718 | 83.7 | 69.7 | 78.7 | 77.8 | | Bing-Chat-0629 | 59.6 | 52.2 | 90.1 | 71.5 | | LLaVA-13B-v1-336px-0719 (beam=1) | 64.3 | 55.9 | 81.7 | 70.1 | | LLaVA-13B-v1-336px-0719 (beam=5) | 68.4 | 59.9 | 84.3 | 73.5 | Note that Bard sometimes refuses to answer questions about images containing humans, and Bing-Chat blurs the human faces in the images. We also provide the benchmark score for the subset without humans. | Approach | Conversation | Detail | Reasoning | Overall | |----------------|--------------|--------|-----------|---------| | Bard-0718 | 94.9 | 74.3 | 84.3 | 84.6 | | Bing-Chat-0629 | 55.8 | 53.6 | 93.5 | 72.6 | | LLaVA-13B-v1-336px-0719 (beam=1) | 62.2 | 56.4 | 82.2 | 70.0 | | LLaVA-13B-v1-336px-0719 (beam=5) | 65.6 | 61.7 | 85.0 | 73.6 | ================================================ FILE: docs/LLaVA_from_LLaMA2.md ================================================ # LLaVA (based on Llama 2 LLM, Preview) *NOTE: This is a technical preview. We are still running hyperparameter search, and will release the final model soon. If you'd like to contribute to this, please contact us.* :llama: **-Introduction-** [Llama 2 is an open-source LLM released by Meta AI](https://about.fb.com/news/2023/07/llama-2/) today (July 18, 2023). Compared with its early version [Llama 1](https://ai.meta.com/blog/large-language-model-llama-meta-ai/), Llama 2 is more favored in ***stronger language performance***, ***longer context window***, and importantly ***commercially usable***! While Llama 2 is changing the LLM market landscape in the language space, its multimodal ability remains unknown. We quickly develop the LLaVA variant based on the latest Llama 2 checkpoints, and release it to the community for the public use. You need to apply for and download the latest Llama 2 checkpoints to start your own training (apply [here](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)) ## Training Please checkout [`pretrain.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/pretrain.sh), [`finetune.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/finetune.sh), [`finetune_lora.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/finetune_lora.sh). ## LLaVA (based on Llama 2), What is different? :volcano: How is the new LLaVA based on Llama 2 different from Llama 1? The comparisons of the training process are described: - **Pre-training**. The pre-trained base LLM is changed from Llama 1 to Llama 2 - **Language instruction-tuning**. The previous LLaVA model starts with Vicuna, which is instruct tuned on ShareGPT data from Llama 1; The new LLaVA model starts with Llama 2 Chat, which is an instruct tuned checkpoint on dialogue data from Llama 2. - **Multimodal instruction-tuning**. The same LLaVA-Lighting process is applied. ### Results - Llama 2 is better at following the instructions of role playing; Llama 2 fails in following the instructions of translation - The quantitative evaluation on [LLaVA-Bench](https://github.com/haotian-liu/LLaVA/blob/main/docs/LLaVA_Bench.md) demonstrates on-par performance between Llama 2 and Llama 1 in LLaVA's multimodal chat ability. ================================================ FILE: docs/LoRA.md ================================================ # LLaVA (LoRA, Preview) NOTE: This is a technical preview, and is not yet ready for production use. We are still running hyperparameter search for the LoRA model, and will release the final model soon. If you'd like to contribute to this, please contact us. You need latest code base for LoRA support (instructions [here](https://github.com/haotian-liu/LLaVA#upgrade-to-latest-code-base)) ## Demo (Web UI) Please execute each of the commands below one by one (after the previous one has finished). The commands are the same as launching other demos except for an additional `--model-base` flag to specify the base model to use. Please make sure the base model corresponds to the LoRA checkpoint that you are using. For this technical preview, you need Vicuna v1.1 (7B) checkpoint (if you do not have that already, follow the instructions [here](https://github.com/lm-sys/FastChat#vicuna-weights)). #### Launch a controller ```Shell python -m llava.serve.controller --host 0.0.0.0 --port 10000 ``` #### Launch a gradio web server. ```Shell python -m llava.serve.gradio_web_server --controller http://localhost:10000 --model-list-mode reload ``` You just launched the Gradio web interface. Now, you can open the web interface with the URL printed on the screen. You may notice that there is no model in the model list. Do not worry, as we have not launched any model worker yet. It will be automatically updated when you launch a model worker. #### Launch a model worker ```Shell python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path liuhaotian/llava-vicuna-7b-v1.1-lcs_558k-instruct_80k_3e-lora-preview-alpha --model-base /path/to/vicuna-v1.1 ``` Wait until the process finishes loading the model and you see "Uvicorn running on ...". Now, refresh your Gradio web UI, and you will see the model you just launched in the model list. You can launch as many workers as you want, and compare between different model checkpoints in the same Gradio interface. Please keep the `--controller` the same, and modify the `--port` and `--worker` to a different port number for each worker. ## Training Please see sample training scripts for [LoRA](https://github.com/haotian-liu/LLaVA/blob/main/scripts/finetune_lora.sh) and [QLoRA](https://github.com/haotian-liu/LLaVA/blob/main/scripts/finetune_qlora.sh). We provide sample DeepSpeed configs, [`zero3.json`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/zero3.json) is more like PyTorch FSDP, and [`zero3_offload.json`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/zero3_offload.json) can further save memory consumption by offloading parameters to CPU. `zero3.json` is usually faster than `zero3_offload.json` but requires more GPU memory, therefore, we recommend trying `zero3.json` first, and if you run out of GPU memory, try `zero3_offload.json`. You can also tweak the `per_device_train_batch_size` and `gradient_accumulation_steps` in the config to save memory, and just to make sure that `per_device_train_batch_size` and `gradient_accumulation_steps` remains the same. If you are having issues with ZeRO-3 configs, and there are enough VRAM, you may try [`zero2.json`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/zero2.json). This consumes slightly more memory than ZeRO-3, and behaves more similar to PyTorch FSDP, while still supporting parameter-efficient tuning. ## Create Merged Checkpoints ```Shell python scripts/merge_lora_weights.py \ --model-path /path/to/lora_model \ --model-base /path/to/base_model \ --save-model-path /path/to/merge_model ``` ================================================ FILE: docs/MODEL_ZOO.md ================================================ # Model Zoo **To Use LLaVA-1.6 checkpoints, your llava package version must be newer than 1.2.0. [Instructions](https://github.com/haotian-liu/LLaVA#upgrade-to-latest-code-base) on how to upgrade.** If you are interested in including any other details in Model Zoo, please open an issue :) The model weights below are *merged* weights. You do not need to apply delta. The usage of LLaVA checkpoints should comply with the base LLM's model license. ## LLaVA-v1.6 | Version | LLM | Schedule | Checkpoint | MMMU | MathVista | VQAv2 | GQA | VizWiz | SQA | TextVQA | POPE | MME | MM-Bench | MM-Bench-CN | SEED-IMG | LLaVA-Bench-Wild | MM-Vet | |----------|----------|-----------|-----------|---|---|---|---|---|---|---|---|---|---|---|---|---|---| | LLaVA-1.6 | Vicuna-7B | full_ft-1e | [liuhaotian/llava-v1.6-vicuna-7b](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-7b) | 35.8 | 34.6 | 81.8 | 64.2 | 57.6 | 70.1 | 64.9 | 86.5 | 1519/332 | 67.4 | 60.6 | 70.2 | 81.6 | 43.9 | | LLaVA-1.6 | Vicuna-13B | full_ft-1e | [liuhaotian/llava-v1.6-vicuna-13b](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-13b) | 36.2 | 35.3 | 82.8 | 65.4 | 60.5 | 73.6 | 67.1 | 86.2 | 1575/326 | 70 | 64.4 | 71.9 | 87.3 | 48.4 | | LLaVA-1.6 | Mistral-7B | full_ft-1e | [liuhaotian/llava-v1.6-mistral-7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b) | 35.3 | 37.7 | 82.2 | 64.8 | 60.0 | 72.8 | 65.7 | 86.7 | 1498/321 | 68.7 | 61.2 | 72.2 | 83.2 | 47.3 | | LLaVA-1.6 | Hermes-Yi-34B | full_ft-1e | [liuhaotian/llava-v1.6-34b](https://huggingface.co/liuhaotian/llava-v1.6-34b) | 51.1 | 46.5 | 83.7 | 67.1 | 63.8 | 81.8 | 69.5 | 87.7 | 1631/397 | 79.3 | 79 | 75.9 | 89.6 | 57.4 | *LLaVA-1.6-34B outperforms Gemini Pro on benchmarks like MMMU and MathVista.* ## LLaVA-v1.5 | Version | Size | Schedule | Checkpoint | VQAv2 | GQA | VizWiz | SQA | TextVQA | POPE | MME | MM-Bench | MM-Bench-CN | SEED | LLaVA-Bench-Wild | MM-Vet | |----------|----------|-----------|-----------|---|---|---|---|---|---|---|---|---|---|---|---| | LLaVA-1.5 | 7B | full_ft-1e | [liuhaotian/llava-v1.5-7b](https://huggingface.co/liuhaotian/llava-v1.5-7b) | 78.5 | 62.0 | 50.0 | 66.8 | 58.2 | 85.9 | 1510.7 | 64.3 | 58.3 | 58.6 | 65.4 | 31.1 | | LLaVA-1.5 | 13B | full_ft-1e | [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) | 80.0 | 63.3 | 53.6 | 71.6 | 61.3 | 85.9 | 1531.3 | 67.7 | 63.6 | 61.6 | 72.5 | 36.1 | | LLaVA-1.5 | 7B | lora-1e | [liuhaotian/llava-v1.5-7b-lora](https://huggingface.co/liuhaotian/llava-v1.5-7b-lora) | 79.1 | 63.0 | 47.8 | 68.4 | 58.2 | 86.4 | 1476.9 | 66.1 | 58.9 | 60.1 | 67.9 | 30.2 | | LLaVA-1.5 | 13B | lora-1e | [liuhaotian/llava-v1.5-13b-lora](https://huggingface.co/liuhaotian/llava-v1.5-13b-lora) | 80.0 | 63.3 | 58.9 | 71.2 | 60.2 | 86.7 | 1541.7 | 68.5 | 61.5 | 61.3 | 69.5 | 38.3 | Base model: Vicuna v1.5. Training logs: [wandb](https://api.wandb.ai/links/lht/6orh56wc).


LLaVA-1.5 achieves SoTA performance across 11 benchmarks.

## LLaVA-v1 *Note: We recommend using the most capable LLaVA-v1.6 series above for the best performance.* | Base LLM | Vision Encoder | Pretrain Data | Pretraining schedule | Finetuning Data | Finetuning schedule | LLaVA-Bench-Conv | LLaVA-Bench-Detail | LLaVA-Bench-Complex | LLaVA-Bench-Overall | Download | |----------|----------------|---------------|----------------------|-----------------|--------------------|------------------|--------------------|---------------------|---------------------|---------------------| | Vicuna-13B-v1.3 | CLIP-L-336px | LCS-558K | 1e | LLaVA-Instruct-80K | proj-1e, lora-1e | 64.3 | 55.9 | 81.7 | 70.1 | [LoRA](https://huggingface.co/liuhaotian/llava-v1-0719-336px-lora-vicuna-13b-v1.3) [LoRA-Merged](https://huggingface.co/liuhaotian/llava-v1-0719-336px-lora-merge-vicuna-13b-v1.3) | | LLaMA-2-13B-Chat | CLIP-L | LCS-558K | 1e | LLaVA-Instruct-80K | full_ft-1e | 56.7 | 58.6 | 80.0 | 67.9 | [ckpt](https://huggingface.co/liuhaotian/llava-llama-2-13b-chat-lightning-preview) | | LLaMA-2-7B-Chat | CLIP-L | LCS-558K | 1e | LLaVA-Instruct-80K | lora-1e | 51.2 | 58.9 | 71.6 | 62.8 | [LoRA](https://huggingface.co/liuhaotian/llava-llama-2-7b-chat-lightning-lora-preview) | ## Projector weights These are projector weights we have pretrained. You can use these projector weights for visual instruction tuning. They are just pretrained on image-text pairs and are NOT instruction-tuned, which means they do NOT follow instructions as well as our official models and can output repetitive, lengthy, and garbled outputs. If you want to have nice conversations with LLaVA, use the checkpoints above (LLaVA v1.6). NOTE: These projector weights are only compatible with `llava>=1.0.0`. Please check out the latest codebase if your local code version is below v1.0.0. NOTE: When you use our pretrained projector for visual instruction tuning, it is very important to use the same base LLM and vision encoder as the one we used for pretraining the projector. Otherwise, the performance will be very poor. When using these projector weights to instruction-tune your LMM, please make sure that these options are correctly set as follows, ```Shell --mm_use_im_start_end False --mm_use_im_patch_token False ``` | Base LLM | Vision Encoder | Projection | Pretrain Data | Pretraining schedule | Download | |----------|----------------|---------------|----------------------|----------|----------| | Vicuna-13B-v1.5 | CLIP-L-336px | MLP-2x | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-v1.5-mlp2x-336px-pretrain-vicuna-13b-v1.5) | | Vicuna-7B-v1.5 | CLIP-L-336px | MLP-2x | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-v1.5-mlp2x-336px-pretrain-vicuna-7b-v1.5) | | LLaMA-2-13B-Chat | CLIP-L-336px | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-336px-pretrain-llama-2-13b-chat) | | LLaMA-2-7B-Chat | CLIP-L-336px | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-336px-pretrain-llama-2-7b-chat) | | LLaMA-2-13B-Chat | CLIP-L | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-pretrain-llama-2-13b-chat) | | LLaMA-2-7B-Chat | CLIP-L | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-pretrain-llama-2-7b-chat) | | Vicuna-13B-v1.3 | CLIP-L-336px | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-336px-pretrain-vicuna-13b-v1.3) | | Vicuna-7B-v1.3 | CLIP-L-336px | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3) | | Vicuna-13B-v1.3 | CLIP-L | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-pretrain-vicuna-13b-v1.3) | | Vicuna-7B-v1.3 | CLIP-L | Linear | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/llava-pretrain-vicuna-7b-v1.3) | ## Science QA Checkpoints | Base LLM | Vision Encoder | Pretrain Data | Pretraining schedule | Finetuning Data | Finetuning schedule | Download | |----------|----------------|---------------|----------------------|-----------------|--------------------|---------------------| | Vicuna-13B-v1.3 | CLIP-L | LCS-558K | 1e | ScienceQA | full_ft-12e | [ckpt](https://huggingface.co/liuhaotian/llava-lcs558k-scienceqa-vicuna-13b-v1.3) | ## Legacy Models (merged weights) The model weights below are *merged* weights. You do not need to apply delta. The usage of LLaVA checkpoints should comply with the base LLM's model license. | Base LLM | Vision Encoder | Pretrain Data | Pretraining schedule | Finetuning Data | Finetuning schedule | Download | |----------|----------------|---------------|----------------------|-----------------|--------------------|------------------| | MPT-7B-Chat | CLIP-L | LCS-558K | 1e | LLaVA-Instruct-80K | full_ft-1e | [preview](https://huggingface.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview) | ## Legacy Models (delta weights) The model weights below are *delta* weights. The usage of LLaVA checkpoints should comply with the base LLM's model license: [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md). You can add our delta to the original LLaMA weights to obtain the LLaVA weights. Instructions: 1. Get the original LLaMA weights in the huggingface format by following the instructions [here](https://huggingface.co/docs/transformers/main/model_doc/llama). 2. Use the following scripts to get LLaVA weights by applying our delta. It will automatically download delta weights from our Hugging Face account. In the script below, we use the delta weights of [`liuhaotian/LLaVA-7b-delta-v0`](https://huggingface.co/liuhaotian/LLaVA-7b-delta-v0) as an example. It can be adapted for other delta weights by changing the `--delta` argument (and base/target accordingly). ```bash python3 -m llava.model.apply_delta \ --base /path/to/llama-7b \ --target /output/path/to/LLaVA-7B-v0 \ --delta liuhaotian/LLaVA-7b-delta-v0 ``` | Base LLM | Vision Encoder | Pretrain Data | Pretraining schedule | Finetuning Data | Finetuning schedule | Download | |----------|----------------|---------------|----------------------|-----------------|--------------------|------------------| | Vicuna-13B-v1.1 | CLIP-L | CC-595K | 1e | LLaVA-Instruct-158K | full_ft-3e | [delta-weights](https://huggingface.co/liuhaotian/LLaVA-13b-delta-v1-1) | | Vicuna-7B-v1.1 | CLIP-L | LCS-558K | 1e | LLaVA-Instruct-80K | full_ft-1e | [delta-weights](https://huggingface.co/liuhaotian/LLaVA-Lightning-7B-delta-v1-1) | | Vicuna-13B-v0 | CLIP-L | CC-595K | 1e | LLaVA-Instruct-158K | full_ft-3e | [delta-weights](https://huggingface.co/liuhaotian/LLaVA-13b-delta-v0) | | Vicuna-13B-v0 | CLIP-L | CC-595K | 1e | ScienceQA | full_ft-12e | [delta-weights](https://huggingface.co/liuhaotian/LLaVA-13b-delta-v0-science_qa) | | Vicuna-7B-v0 | CLIP-L | CC-595K | 1e | LLaVA-Instruct-158K | full_ft-3e | [delta-weights](https://huggingface.co/liuhaotian/LLaVA-7b-delta-v0) | ## Legacy Projector weights The following projector weights are deprecated, and the support for them may be removed in the future. They do not support zero-shot inference. Please use the projector weights in the [table above](#projector-weights) if possible. **NOTE**: When you use our pretrained projector for visual instruction tuning, it is very important to **use the same base LLM and vision encoder** as the one we used for pretraining the projector. Otherwise, the performance will be very bad. When using these projector weights to instruction tune your LMM, please make sure that these options are correctly set as follows, ```Shell --mm_use_im_start_end True --mm_use_im_patch_token False ``` | Base LLM | Vision Encoder | Pretrain Data | Pretraining schedule | Download | |----------|----------------|---------------|----------------------|----------| | Vicuna-7B-v1.1 | CLIP-L | LCS-558K | 1e | [projector](https://huggingface.co/liuhaotian/LLaVA-Pretrained-Projectors/blob/main/LLaVA-7b-pretrain-projector-v1-1-LCS-558K-blip_caption.bin) | | Vicuna-13B-v0 | CLIP-L | CC-595K | 1e | [projector](https://huggingface.co/liuhaotian/LLaVA-Pretrained-Projectors/blob/main/LLaVA-13b-pretrain-projector-v0-CC3M-595K-original_caption.bin) | | Vicuna-7B-v0 | CLIP-L | CC-595K | 1e | [projector](https://huggingface.co/liuhaotian/LLaVA-Pretrained-Projectors/blob/main/LLaVA-7b-pretrain-projector-v0-CC3M-595K-original_caption.bin) | When using these projector weights to instruction tune your LMM, please make sure that these options are correctly set as follows, ```Shell --mm_use_im_start_end False --mm_use_im_patch_token False ``` | Base LLM | Vision Encoder | Pretrain Data | Pretraining schedule | Download | |----------|----------------|---------------|----------------------|----------| | Vicuna-13B-v0 | CLIP-L | CC-595K | 1e | [projector](https://huggingface.co/liuhaotian/LLaVA-Pretrained-Projectors/blob/main/LLaVA-13b-pretrain-projector-v0-CC3M-595K-original_caption-no_im_token.bin) | ================================================ FILE: docs/ScienceQA.md ================================================ ### ScienceQA #### Prepare Data 1. Please see ScienceQA [repo](https://github.com/lupantech/ScienceQA) for setting up the dataset. 2. Generate ScienceQA dataset for LLaVA conversation-style format. ```Shell python scripts/convert_sqa_to_llava.py \ convert_to_llava \ --base-dir /path/to/ScienceQA/data/scienceqa \ --prompt-format "QCM-LEA" \ --split {train,val,minival,test,minitest} ``` #### Training 1. Pretraining You can download our pretrained projector weights from our [Model Zoo](), or train your own projector weights using [`pretrain.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/pretrain.sh). 2. Finetuning See [`finetune_sqa.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/finetune_sqa.sh). #### Evaluation 1. Multiple-GPU inference You may evaluate this with multiple GPUs, and concatenate the generated jsonl files. Please refer to our script for [batch evaluation](https://github.com/haotian-liu/LLaVA/blob/main/scripts/sqa_eval_batch.sh) and [results gathering](https://github.com/haotian-liu/LLaVA/blob/main/scripts/sqa_eval_gather.sh). 2. Single-GPU inference (a) Generate LLaVA responses on ScienceQA dataset ```Shell python -m llava.eval.model_vqa_science \ --model-path liuhaotian/llava-lcs558k-scienceqa-vicuna-13b-v1.3 \ --question-file /path/to/ScienceQA/data/scienceqa/llava_test_QCM-LEA.json \ --image-folder /path/to/ScienceQA/data/scienceqa/images/test \ --answers-file vqa/results/ScienceQA/test_llava-13b.jsonl \ --conv-mode llava_v1 ``` (b) Evaluate the generated responses ```Shell python eval_science_qa.py \ --base-dir /path/to/ScienceQA/data/scienceqa \ --result-file vqa/results/ScienceQA/test_llava-13b.jsonl \ --output-file vqa/results/ScienceQA/test_llava-13b_output.json \ --output-result vqa/results/ScienceQA/test_llava-13b_result.json \ ``` For reference, we attach our prediction file [`test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json`](https://github.com/haotian-liu/LLaVA/blob/main/llava/eval/table/results/test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json) and [`test_sqa_llava_13b_v0.json`](https://github.com/haotian-liu/LLaVA/blob/main/llava/eval/table/results/test_sqa_llava_13b_v0.json) for comparison when reproducing our results, as well as for further analysis in detail. ================================================ FILE: docs/Windows.md ================================================ # Run LLaVA on Windows *NOTE: LLaVA on Windows is not fully supported. Currently we only support 16-bit inference. For a more complete support, please use [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) for now. More functionalities on Windows is to be added soon, stay tuned.* ## Installation 1. Clone this repository and navigate to LLaVA folder ```bash git clone https://github.com/haotian-liu/LLaVA.git cd LLaVA ``` 2. Install Package ```Shell conda create -n llava python=3.10 -y conda activate llava python -m pip install --upgrade pip # enable PEP 660 support pip install torch==2.0.1+cu117 torchvision==0.15.2+cu117 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu117 pip install -e . pip uninstall bitsandbytes ``` ## Run demo See instructions [here](https://github.com/haotian-liu/LLaVA#demo). Note that quantization (4-bit, 8-bit) is *NOT* supported on Windows. Stay tuned for the 4-bit support on Windows! ================================================ FILE: docs/macOS.md ================================================ # Run LLaVA on macOS *NOTE: LLaVA on macOS is not fully supported. Currently we only support 16-bit inference. More functionalities on macOS is to be added soon, stay tuned.* ## Installation 1. Clone this repository and navigate to LLaVA folder ```bash git clone https://github.com/haotian-liu/LLaVA.git cd LLaVA ``` 2. Install Package ```Shell conda create -n llava python=3.10 -y conda activate llava python -mpip install --upgrade pip # enable PEP 660 support pip install -e . pip install torch==2.1.0 torchvision==0.16.0 pip uninstall bitsandbytes ``` ## Run demo Specify `--device mps` when launching model worker or CLI. See instructions [here](https://github.com/haotian-liu/LLaVA#demo). Note that quantization (4-bit, 8-bit) is *NOT* supported on macOS. Stay tuned for the 4-bit support on macOS! ================================================ FILE: llava/__init__.py ================================================ from .model import LlavaLlamaForCausalLM ================================================ FILE: llava/constants.py ================================================ CONTROLLER_HEART_BEAT_EXPIRATION = 30 WORKER_HEART_BEAT_INTERVAL = 15 LOGDIR = "." # Model Constants IGNORE_INDEX = -100 IMAGE_TOKEN_INDEX = -200 DEFAULT_IMAGE_TOKEN = "" DEFAULT_IMAGE_PATCH_TOKEN = "" DEFAULT_IM_START_TOKEN = "" DEFAULT_IM_END_TOKEN = "" IMAGE_PLACEHOLDER = "" ================================================ FILE: llava/conversation.py ================================================ import dataclasses from enum import auto, Enum from typing import List, Tuple import base64 from io import BytesIO from PIL import Image class SeparatorStyle(Enum): """Different separator style.""" SINGLE = auto() TWO = auto() MPT = auto() PLAIN = auto() LLAMA_2 = auto() @dataclasses.dataclass class Conversation: """A class that keeps all conversation history.""" system: str roles: List[str] messages: List[List[str]] offset: int sep_style: SeparatorStyle = SeparatorStyle.SINGLE sep: str = "###" sep2: str = None version: str = "Unknown" skip_next: bool = False def get_prompt(self): messages = self.messages if len(messages) > 0 and type(messages[0][1]) is tuple: messages = self.messages.copy() init_role, init_msg = messages[0].copy() init_msg = init_msg[0].replace("", "").strip() if 'mmtag' in self.version: messages[0] = (init_role, init_msg) messages.insert(0, (self.roles[0], "")) messages.insert(1, (self.roles[1], "Received.")) else: messages[0] = (init_role, "\n" + init_msg) if self.sep_style == SeparatorStyle.SINGLE: ret = self.system + self.sep for role, message in messages: if message: if type(message) is tuple: message, _, _ = message ret += role + ": " + message + self.sep else: ret += role + ":" elif self.sep_style == SeparatorStyle.TWO: seps = [self.sep, self.sep2] ret = self.system + seps[0] for i, (role, message) in enumerate(messages): if message: if type(message) is tuple: message, _, _ = message ret += role + ": " + message + seps[i % 2] else: ret += role + ":" elif self.sep_style == SeparatorStyle.MPT: ret = self.system + self.sep for role, message in messages: if message: if type(message) is tuple: message, _, _ = message ret += role + message + self.sep else: ret += role elif self.sep_style == SeparatorStyle.LLAMA_2: wrap_sys = lambda msg: f"<>\n{msg}\n<>\n\n" if len(msg) > 0 else msg wrap_inst = lambda msg: f"[INST] {msg} [/INST]" ret = "" for i, (role, message) in enumerate(messages): if i == 0: assert message, "first message should not be none" assert role == self.roles[0], "first message should come from user" if message: if type(message) is tuple: message, _, _ = message if i == 0: message = wrap_sys(self.system) + message if i % 2 == 0: message = wrap_inst(message) ret += self.sep + message else: ret += " " + message + " " + self.sep2 else: ret += "" ret = ret.lstrip(self.sep) elif self.sep_style == SeparatorStyle.PLAIN: seps = [self.sep, self.sep2] ret = self.system for i, (role, message) in enumerate(messages): if message: if type(message) is tuple: message, _, _ = message ret += message + seps[i % 2] else: ret += "" else: raise ValueError(f"Invalid style: {self.sep_style}") return ret def append_message(self, role, message): self.messages.append([role, message]) def process_image(self, image, image_process_mode, return_pil=False, image_format='PNG', max_len=1344, min_len=672): if image_process_mode == "Pad": def expand2square(pil_img, background_color=(122, 116, 104)): width, height = pil_img.size if width == height: return pil_img elif width > height: result = Image.new(pil_img.mode, (width, width), background_color) result.paste(pil_img, (0, (width - height) // 2)) return result else: result = Image.new(pil_img.mode, (height, height), background_color) result.paste(pil_img, ((height - width) // 2, 0)) return result image = expand2square(image) elif image_process_mode in ["Default", "Crop"]: pass elif image_process_mode == "Resize": image = image.resize((336, 336)) else: raise ValueError(f"Invalid image_process_mode: {image_process_mode}") if max(image.size) > max_len: max_hw, min_hw = max(image.size), min(image.size) aspect_ratio = max_hw / min_hw shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw)) longest_edge = int(shortest_edge * aspect_ratio) W, H = image.size if H > W: H, W = longest_edge, shortest_edge else: H, W = shortest_edge, longest_edge image = image.resize((W, H)) if return_pil: return image else: buffered = BytesIO() image.save(buffered, format=image_format) img_b64_str = base64.b64encode(buffered.getvalue()).decode() return img_b64_str def get_images(self, return_pil=False): images = [] for i, (role, msg) in enumerate(self.messages[self.offset:]): if i % 2 == 0: if type(msg) is tuple: msg, image, image_process_mode = msg image = self.process_image(image, image_process_mode, return_pil=return_pil) images.append(image) return images def to_gradio_chatbot(self): ret = [] for i, (role, msg) in enumerate(self.messages[self.offset:]): if i % 2 == 0: if type(msg) is tuple: msg, image, image_process_mode = msg img_b64_str = self.process_image( image, "Default", return_pil=False, image_format='JPEG') img_str = f'user upload image' msg = img_str + msg.replace('', '').strip() ret.append([msg, None]) else: ret.append([msg, None]) else: ret[-1][-1] = msg return ret def copy(self): return Conversation( system=self.system, roles=self.roles, messages=[[x, y] for x, y in self.messages], offset=self.offset, sep_style=self.sep_style, sep=self.sep, sep2=self.sep2, version=self.version) def dict(self): if len(self.get_images()) > 0: return { "system": self.system, "roles": self.roles, "messages": [[x, y[0] if type(y) is tuple else y] for x, y in self.messages], "offset": self.offset, "sep": self.sep, "sep2": self.sep2, } return { "system": self.system, "roles": self.roles, "messages": self.messages, "offset": self.offset, "sep": self.sep, "sep2": self.sep2, } conv_vicuna_v0 = Conversation( system="A chat between a curious human and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the human's questions.", roles=("Human", "Assistant"), messages=( ("Human", "What are the key differences between renewable and non-renewable energy sources?"), ("Assistant", "Renewable energy sources are those that can be replenished naturally in a relatively " "short amount of time, such as solar, wind, hydro, geothermal, and biomass. " "Non-renewable energy sources, on the other hand, are finite and will eventually be " "depleted, such as coal, oil, and natural gas. Here are some key differences between " "renewable and non-renewable energy sources:\n" "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable " "energy sources are finite and will eventually run out.\n" "2. Environmental impact: Renewable energy sources have a much lower environmental impact " "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, " "and other negative effects.\n" "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically " "have lower operational costs than non-renewable sources.\n" "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote " "locations than non-renewable sources.\n" "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different " "situations and needs, while non-renewable sources are more rigid and inflexible.\n" "6. Sustainability: Renewable energy sources are more sustainable over the long term, while " "non-renewable sources are not, and their depletion can lead to economic and social instability.\n") ), offset=2, sep_style=SeparatorStyle.SINGLE, sep="###", ) conv_vicuna_v1 = Conversation( system="A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions.", roles=("USER", "ASSISTANT"), version="v1", messages=(), offset=0, sep_style=SeparatorStyle.TWO, sep=" ", sep2="", ) conv_llama_2 = Conversation( system="""You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""", roles=("USER", "ASSISTANT"), version="llama_v2", messages=(), offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_llava_llama_2 = Conversation( system="You are a helpful language and vision assistant. " "You are able to understand the visual content that the user provides, " "and assist the user with a variety of tasks using natural language.", roles=("USER", "ASSISTANT"), version="llama_v2", messages=(), offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_mpt = Conversation( system="""<|im_start|>system A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""", roles=("<|im_start|>user\n", "<|im_start|>assistant\n"), version="mpt", messages=(), offset=0, sep_style=SeparatorStyle.MPT, sep="<|im_end|>", ) conv_llava_plain = Conversation( system="", roles=("", ""), messages=( ), offset=0, sep_style=SeparatorStyle.PLAIN, sep="\n", ) conv_llava_v0 = Conversation( system="A chat between a curious human and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the human's questions.", roles=("Human", "Assistant"), messages=( ), offset=0, sep_style=SeparatorStyle.SINGLE, sep="###", ) conv_llava_v0_mmtag = Conversation( system="A chat between a curious user and an artificial intelligence assistant. " "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." "The visual content will be provided with the following format: visual content.", roles=("Human", "Assistant"), messages=( ), offset=0, sep_style=SeparatorStyle.SINGLE, sep="###", version="v0_mmtag", ) conv_llava_v1 = Conversation( system="A chat between a curious human and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the human's questions.", roles=("USER", "ASSISTANT"), version="v1", messages=(), offset=0, sep_style=SeparatorStyle.TWO, sep=" ", sep2="", ) conv_llava_v1_mmtag = Conversation( system="A chat between a curious user and an artificial intelligence assistant. " "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." "The visual content will be provided with the following format: visual content.", roles=("USER", "ASSISTANT"), messages=(), offset=0, sep_style=SeparatorStyle.TWO, sep=" ", sep2="", version="v1_mmtag", ) conv_mistral_instruct = Conversation( system="", roles=("USER", "ASSISTANT"), version="llama_v2", messages=(), offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_chatml_direct = Conversation( system="""<|im_start|>system Answer the questions.""", roles=("<|im_start|>user\n", "<|im_start|>assistant\n"), version="mpt", messages=(), offset=0, sep_style=SeparatorStyle.MPT, sep="<|im_end|>", ) default_conversation = conv_vicuna_v1 conv_templates = { "default": conv_vicuna_v0, "v0": conv_vicuna_v0, "v1": conv_vicuna_v1, "vicuna_v1": conv_vicuna_v1, "llama_2": conv_llama_2, "mistral_instruct": conv_mistral_instruct, "chatml_direct": conv_chatml_direct, "mistral_direct": conv_chatml_direct, "plain": conv_llava_plain, "v0_plain": conv_llava_plain, "llava_v0": conv_llava_v0, "v0_mmtag": conv_llava_v0_mmtag, "llava_v1": conv_llava_v1, "v1_mmtag": conv_llava_v1_mmtag, "llava_llama_2": conv_llava_llama_2, "mpt": conv_mpt, } if __name__ == "__main__": print(default_conversation.get_prompt()) ================================================ FILE: llava/eval/eval_gpt_review.py ================================================ import argparse import json import os import openai import tqdm import ray import time NUM_SECONDS_TO_SLEEP = 3 @ray.remote(num_cpus=4) def get_eval(content: str, max_tokens: int): while True: try: response = openai.ChatCompletion.create( model='gpt-4', messages=[{ 'role': 'system', 'content': 'You are a helpful and precise assistant for checking the quality of the answer.' }, { 'role': 'user', 'content': content, }], temperature=0.2, # TODO: figure out which temperature is best for evaluation max_tokens=max_tokens, ) break except openai.error.RateLimitError: pass except Exception as e: print(e) time.sleep(NUM_SECONDS_TO_SLEEP) print('success!') return response['choices'][0]['message']['content'] def parse_score(review): try: score_pair = review.split('\n')[0] score_pair = score_pair.replace(',', ' ') sp = score_pair.split(' ') if len(sp) == 2: return [float(sp[0]), float(sp[1])] else: print('error', review) return [-1, -1] except Exception as e: print(e) print('error', review) return [-1, -1] if __name__ == '__main__': parser = argparse.ArgumentParser(description='ChatGPT-based QA evaluation.') parser.add_argument('-q', '--question') # parser.add_argument('-a', '--answer') parser.add_argument('-a', '--answer-list', nargs='+', default=[]) parser.add_argument('-r', '--rule') parser.add_argument('-o', '--output') parser.add_argument('--max-tokens', type=int, default=1024, help='maximum number of tokens produced in the output') args = parser.parse_args() ray.init() f_q = open(os.path.expanduser(args.question)) f_ans1 = open(os.path.expanduser(args.answer_list[0])) f_ans2 = open(os.path.expanduser(args.answer_list[1])) rule_dict = json.load(open(os.path.expanduser(args.rule), 'r')) review_file = open(f'{args.output}', 'w') js_list = [] handles = [] idx = 0 for ques_js, ans1_js, ans2_js in zip(f_q, f_ans1, f_ans2): # if idx == 1: # break ques = json.loads(ques_js) ans1 = json.loads(ans1_js) ans2 = json.loads(ans2_js) category = json.loads(ques_js)['category'] if category in rule_dict: rule = rule_dict[category] else: rule = rule_dict['default'] prompt = rule['prompt'] role = rule['role'] content = (f'[Question]\n{ques["text"]}\n\n' f'[{role} 1]\n{ans1["text"]}\n\n[End of {role} 1]\n\n' f'[{role} 2]\n{ans2["text"]}\n\n[End of {role} 2]\n\n' f'[System]\n{prompt}\n\n') js_list.append({ 'id': idx+1, 'question_id': ques['question_id'], 'answer1_id': ans1['answer_id'], 'answer2_id': ans2['answer_id'], 'category': category}) idx += 1 handles.append(get_eval.remote(content, args.max_tokens)) # To avoid the rate limit set by OpenAI time.sleep(NUM_SECONDS_TO_SLEEP) reviews = ray.get(handles) for idx, review in enumerate(reviews): scores = parse_score(review) js_list[idx]['content'] = review js_list[idx]['tuple'] = scores review_file.write(json.dumps(js_list[idx]) + '\n') review_file.close() ================================================ FILE: llava/eval/eval_gpt_review_bench.py ================================================ import argparse import json import os import openai import time NUM_SECONDS_TO_SLEEP = 0.5 def get_eval(content: str, max_tokens: int): while True: try: response = openai.ChatCompletion.create( model='gpt-4-0314', messages=[{ 'role': 'system', 'content': 'You are a helpful and precise assistant for checking the quality of the answer.' }, { 'role': 'user', 'content': content, }], temperature=0.2, # TODO: figure out which temperature is best for evaluation max_tokens=max_tokens, ) break except openai.error.RateLimitError: pass except Exception as e: print(e) time.sleep(NUM_SECONDS_TO_SLEEP) return response['choices'][0]['message']['content'] def parse_score(review): try: score_pair = review.split('\n')[0] score_pair = score_pair.replace(',', ' ') sp = score_pair.split(' ') if len(sp) == 2: return [float(sp[0]), float(sp[1])] else: print('error', review) return [-1, -1] except Exception as e: print(e) print('error', review) return [-1, -1] if __name__ == '__main__': parser = argparse.ArgumentParser(description='ChatGPT-based QA evaluation.') parser.add_argument('-q', '--question') parser.add_argument('-c', '--context') parser.add_argument('-a', '--answer-list', nargs='+', default=[]) parser.add_argument('-r', '--rule') parser.add_argument('-o', '--output') parser.add_argument('--max-tokens', type=int, default=1024, help='maximum number of tokens produced in the output') args = parser.parse_args() f_q = open(os.path.expanduser(args.question)) f_ans1 = open(os.path.expanduser(args.answer_list[0])) f_ans2 = open(os.path.expanduser(args.answer_list[1])) rule_dict = json.load(open(os.path.expanduser(args.rule), 'r')) if os.path.isfile(os.path.expanduser(args.output)): cur_reviews = [json.loads(line) for line in open(os.path.expanduser(args.output))] else: cur_reviews = [] review_file = open(f'{args.output}', 'a') context_list = [json.loads(line) for line in open(os.path.expanduser(args.context))] image_to_context = {context['image']: context for context in context_list} handles = [] idx = 0 for ques_js, ans1_js, ans2_js in zip(f_q, f_ans1, f_ans2): ques = json.loads(ques_js) ans1 = json.loads(ans1_js) ans2 = json.loads(ans2_js) inst = image_to_context[ques['image']] if isinstance(inst['caption'], list): cap_str = '\n'.join(inst['caption']) else: cap_str = inst['caption'] category = 'llava_bench_' + json.loads(ques_js)['category'] if category in rule_dict: rule = rule_dict[category] else: assert False, f"Visual QA category not found in rule file: {category}." prompt = rule['prompt'] role = rule['role'] content = (f'[Context]\n{cap_str}\n\n' f'[Question]\n{ques["text"]}\n\n' f'[{role} 1]\n{ans1["text"]}\n\n[End of {role} 1]\n\n' f'[{role} 2]\n{ans2["text"]}\n\n[End of {role} 2]\n\n' f'[System]\n{prompt}\n\n') cur_js = { 'id': idx+1, 'question_id': ques['question_id'], 'answer1_id': ans1.get('answer_id', ans1['question_id']), 'answer2_id': ans2.get('answer_id', ans2['answer_id']), 'category': category } if idx >= len(cur_reviews): review = get_eval(content, args.max_tokens) scores = parse_score(review) cur_js['content'] = review cur_js['tuple'] = scores review_file.write(json.dumps(cur_js) + '\n') review_file.flush() else: print(f'Skipping {idx} as we already have it.') idx += 1 print(idx) review_file.close() ================================================ FILE: llava/eval/eval_gpt_review_visual.py ================================================ import argparse import json import os import openai import time NUM_SECONDS_TO_SLEEP = 0.5 def get_eval(content: str, max_tokens: int): while True: try: response = openai.ChatCompletion.create( model='gpt-4-0314', messages=[{ 'role': 'system', 'content': 'You are a helpful and precise assistant for checking the quality of the answer.' }, { 'role': 'user', 'content': content, }], temperature=0.2, # TODO: figure out which temperature is best for evaluation max_tokens=max_tokens, ) break except openai.error.RateLimitError: pass except Exception as e: print(e) time.sleep(NUM_SECONDS_TO_SLEEP) return response['choices'][0]['message']['content'] def parse_score(review): try: score_pair = review.split('\n')[0] score_pair = score_pair.replace(',', ' ') sp = score_pair.split(' ') if len(sp) == 2: return [float(sp[0]), float(sp[1])] else: print('error', review) return [-1, -1] except Exception as e: print(e) print('error', review) return [-1, -1] if __name__ == '__main__': parser = argparse.ArgumentParser(description='ChatGPT-based QA evaluation.') parser.add_argument('-q', '--question') parser.add_argument('-c', '--context') parser.add_argument('-a', '--answer-list', nargs='+', default=[]) parser.add_argument('-r', '--rule') parser.add_argument('-o', '--output') parser.add_argument('--max-tokens', type=int, default=1024, help='maximum number of tokens produced in the output') args = parser.parse_args() f_q = open(os.path.expanduser(args.question)) f_ans1 = open(os.path.expanduser(args.answer_list[0])) f_ans2 = open(os.path.expanduser(args.answer_list[1])) rule_dict = json.load(open(os.path.expanduser(args.rule), 'r')) if os.path.isfile(os.path.expanduser(args.output)): cur_reviews = [json.loads(line) for line in open(os.path.expanduser(args.output))] else: cur_reviews = [] review_file = open(f'{args.output}', 'a') context_list = [json.loads(line) for line in open(os.path.expanduser(args.context))] image_to_context = {context['image']: context for context in context_list} handles = [] idx = 0 for ques_js, ans1_js, ans2_js in zip(f_q, f_ans1, f_ans2): ques = json.loads(ques_js) ans1 = json.loads(ans1_js) ans2 = json.loads(ans2_js) inst = image_to_context[ques['image']] cap_str = '\n'.join(inst['captions']) box_str = '\n'.join([f'{instance["category"]}: {instance["bbox"]}' for instance in inst['instances']]) category = json.loads(ques_js)['category'] if category in rule_dict: rule = rule_dict[category] else: assert False, f"Visual QA category not found in rule file: {category}." prompt = rule['prompt'] role = rule['role'] content = (f'[Context]\n{cap_str}\n\n{box_str}\n\n' f'[Question]\n{ques["text"]}\n\n' f'[{role} 1]\n{ans1["text"]}\n\n[End of {role} 1]\n\n' f'[{role} 2]\n{ans2["text"]}\n\n[End of {role} 2]\n\n' f'[System]\n{prompt}\n\n') cur_js = { 'id': idx+1, 'question_id': ques['question_id'], 'answer1_id': ans1.get('answer_id', ans1['question_id']), 'answer2_id': ans2.get('answer_id', ans2['answer_id']), 'category': category } if idx >= len(cur_reviews): review = get_eval(content, args.max_tokens) scores = parse_score(review) cur_js['content'] = review cur_js['tuple'] = scores review_file.write(json.dumps(cur_js) + '\n') review_file.flush() else: print(f'Skipping {idx} as we already have it.') idx += 1 print(idx) review_file.close() ================================================ FILE: llava/eval/eval_pope.py ================================================ import os import json import argparse def eval_pope(answers, label_file): label_list = [json.loads(q)['label'] for q in open(label_file, 'r')] for answer in answers: text = answer['text'] # Only keep the first sentence if text.find('.') != -1: text = text.split('.')[0] text = text.replace(',', '') words = text.split(' ') if 'No' in words or 'not' in words or 'no' in words: answer['text'] = 'no' else: answer['text'] = 'yes' for i in range(len(label_list)): if label_list[i] == 'no': label_list[i] = 0 else: label_list[i] = 1 pred_list = [] for answer in answers: if answer['text'] == 'no': pred_list.append(0) else: pred_list.append(1) pos = 1 neg = 0 yes_ratio = pred_list.count(1) / len(pred_list) TP, TN, FP, FN = 0, 0, 0, 0 for pred, label in zip(pred_list, label_list): if pred == pos and label == pos: TP += 1 elif pred == pos and label == neg: FP += 1 elif pred == neg and label == neg: TN += 1 elif pred == neg and label == pos: FN += 1 print('TP\tFP\tTN\tFN\t') print('{}\t{}\t{}\t{}'.format(TP, FP, TN, FN)) precision = float(TP) / float(TP + FP) recall = float(TP) / float(TP + FN) f1 = 2*precision*recall / (precision + recall) acc = (TP + TN) / (TP + TN + FP + FN) print('Accuracy: {}'.format(acc)) print('Precision: {}'.format(precision)) print('Recall: {}'.format(recall)) print('F1 score: {}'.format(f1)) print('Yes ratio: {}'.format(yes_ratio)) print('%.3f, %.3f, %.3f, %.3f, %.3f' % (f1, acc, precision, recall, yes_ratio) ) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--annotation-dir", type=str) parser.add_argument("--question-file", type=str) parser.add_argument("--result-file", type=str) args = parser.parse_args() questions = [json.loads(line) for line in open(args.question_file)] questions = {question['question_id']: question for question in questions} answers = [json.loads(q) for q in open(args.result_file)] for file in os.listdir(args.annotation_dir): assert file.startswith('coco_pope_') assert file.endswith('.json') category = file[10:-5] cur_answers = [x for x in answers if questions[x['question_id']]['category'] == category] print('Category: {}, # samples: {}'.format(category, len(cur_answers))) eval_pope(cur_answers, os.path.join(args.annotation_dir, file)) print("====================================") ================================================ FILE: llava/eval/eval_science_qa.py ================================================ import argparse import json import os import re import random def get_args(): parser = argparse.ArgumentParser() parser.add_argument('--base-dir', type=str) parser.add_argument('--result-file', type=str) parser.add_argument('--output-file', type=str) parser.add_argument('--output-result', type=str) parser.add_argument('--split', type=str, default='test') parser.add_argument('--options', type=list, default=["A", "B", "C", "D", "E"]) return parser.parse_args() def convert_caps(results): fakecaps = [] for result in results: image_id = result['question_id'] caption = result['text'] fakecaps.append({"image_id": int(image_id), "caption": caption}) return fakecaps def get_pred_idx(prediction, choices, options): """ Get the index (e.g. 2) from the prediction (e.g. 'C') """ if prediction in options[:len(choices)]: return options.index(prediction) else: return -1 return random.choice(range(len(choices))) if __name__ == "__main__": args = get_args() base_dir = args.base_dir split_indices = json.load(open(os.path.join(base_dir, "pid_splits.json")))[args.split] problems = json.load(open(os.path.join(base_dir, "problems.json"))) predictions = [json.loads(line) for line in open(args.result_file)] predictions = {pred['question_id']: pred for pred in predictions} split_problems = {idx: problems[idx] for idx in split_indices} results = {'correct': [], 'incorrect': []} sqa_results = {} sqa_results['acc'] = None sqa_results['correct'] = None sqa_results['count'] = None sqa_results['results'] = {} sqa_results['outputs'] = {} for prob_id, prob in split_problems.items(): if prob_id not in predictions: pred = {'text': 'FAILED', 'prompt': 'Unknown'} pred_text = 'FAILED' else: pred = predictions[prob_id] pred_text = pred['text'] if pred_text in args.options: answer = pred_text elif len(pred_text) >= 3 and pred_text[0] in args.options and pred_text[1:3] == ". ": answer = pred_text[0] else: pattern = re.compile(r'The answer is ([A-Z]).') res = pattern.findall(pred_text) if len(res) == 1: answer = res[0] # 'A', 'B', ... else: answer = "FAILED" pred_idx = get_pred_idx(answer, prob['choices'], args.options) analysis = { 'question_id': prob_id, 'parsed_ans': answer, 'ground_truth': args.options[prob['answer']], 'question': pred['prompt'], 'pred': pred_text, 'is_multimodal': '' in pred['prompt'], } sqa_results['results'][prob_id] = get_pred_idx(answer, prob['choices'], args.options) sqa_results['outputs'][prob_id] = pred_text if pred_idx == prob['answer']: results['correct'].append(analysis) else: results['incorrect'].append(analysis) correct = len(results['correct']) total = len(results['correct']) + len(results['incorrect']) ###### IMG ###### multimodal_correct = len([x for x in results['correct'] if x['is_multimodal']]) multimodal_incorrect = len([x for x in results['incorrect'] if x['is_multimodal']]) multimodal_total = multimodal_correct + multimodal_incorrect ###### IMG ###### print(f'Total: {total}, Correct: {correct}, Accuracy: {correct / total * 100:.2f}%, IMG-Accuracy: {multimodal_correct / multimodal_total * 100:.2f}%') sqa_results['acc'] = correct / total * 100 sqa_results['correct'] = correct sqa_results['count'] = total with open(args.output_file, 'w') as f: json.dump(results, f, indent=2) with open(args.output_result, 'w') as f: json.dump(sqa_results, f, indent=2) ================================================ FILE: llava/eval/eval_science_qa_gpt4.py ================================================ import argparse import json import os import re import random from collections import defaultdict def get_args(): parser = argparse.ArgumentParser() parser.add_argument('--base-dir', type=str) parser.add_argument('--gpt4-result', type=str) parser.add_argument('--our-result', type=str) parser.add_argument('--split', type=str, default='test') parser.add_argument('--options', type=list, default=["A", "B", "C", "D", "E"]) return parser.parse_args() def convert_caps(results): fakecaps = [] for result in results: image_id = result['question_id'] caption = result['text'] fakecaps.append({"image_id": int(image_id), "caption": caption}) return fakecaps def get_pred_idx(prediction, choices, options): """ Get the index (e.g. 2) from the prediction (e.g. 'C') """ if prediction in options[:len(choices)]: return options.index(prediction) else: return random.choice(range(len(choices))) if __name__ == "__main__": args = get_args() base_dir = args.base_dir split_indices = json.load(open(os.path.join(base_dir, "pid_splits.json")))[args.split] problems = json.load(open(os.path.join(base_dir, "problems.json"))) our_predictions = [json.loads(line) for line in open(args.our_result)] our_predictions = {pred['question_id']: pred for pred in our_predictions} split_problems = {idx: problems[idx] for idx in split_indices} gpt4_predictions = json.load(open(args.gpt4_result))['outputs'] results = defaultdict(lambda: 0) for prob_id, prob in split_problems.items(): if prob_id not in our_predictions: continue if prob_id not in gpt4_predictions: continue our_pred = our_predictions[prob_id]['text'] gpt4_pred = gpt4_predictions[prob_id] pattern = re.compile(r'The answer is ([A-Z]).') our_res = pattern.findall(our_pred) if len(our_res) == 1: our_answer = our_res[0] # 'A', 'B', ... else: our_answer = "FAILED" gpt4_res = pattern.findall(gpt4_pred) if len(gpt4_res) == 1: gpt4_answer = gpt4_res[0] # 'A', 'B', ... else: gpt4_answer = "FAILED" our_pred_idx = get_pred_idx(our_answer, prob['choices'], args.options) gpt4_pred_idx = get_pred_idx(gpt4_answer, prob['choices'], args.options) if gpt4_answer == 'FAILED': results['gpt4_failed'] += 1 # continue gpt4_pred_idx = our_pred_idx # if our_pred_idx != prob['answer']: # print(our_predictions[prob_id]['prompt']) # print('-----------------') # print(f'LECTURE: {prob["lecture"]}') # print(f'SOLUTION: {prob["solution"]}') # print('=====================') else: # continue pass # gpt4_pred_idx = our_pred_idx if gpt4_pred_idx == prob['answer']: results['correct'] += 1 else: results['incorrect'] += 1 if gpt4_pred_idx == prob['answer'] or our_pred_idx == prob['answer']: results['correct_upperbound'] += 1 correct = results['correct'] total = results['correct'] + results['incorrect'] print(f'Total: {total}, Correct: {correct}, Accuracy: {correct / total * 100:.2f}%') print(f'Total: {total}, Correct (upper): {results["correct_upperbound"]}, Accuracy: {results["correct_upperbound"] / total * 100:.2f}%') print(f'Total: {total}, GPT-4 NO-ANS (RANDOM): {results["gpt4_failed"]}, Percentage: {results["gpt4_failed"] / total * 100:.2f}%') ================================================ FILE: llava/eval/eval_science_qa_gpt4_requery.py ================================================ import argparse import json import os import re import random from collections import defaultdict def get_args(): parser = argparse.ArgumentParser() parser.add_argument('--base-dir', type=str) parser.add_argument('--gpt4-result', type=str) parser.add_argument('--requery-result', type=str) parser.add_argument('--our-result', type=str) parser.add_argument('--output-result', type=str) parser.add_argument('--split', type=str, default='test') parser.add_argument('--options', type=list, default=["A", "B", "C", "D", "E"]) return parser.parse_args() def convert_caps(results): fakecaps = [] for result in results: image_id = result['question_id'] caption = result['text'] fakecaps.append({"image_id": int(image_id), "caption": caption}) return fakecaps def get_pred_idx(prediction, choices, options): """ Get the index (e.g. 2) from the prediction (e.g. 'C') """ if prediction in options[:len(choices)]: return options.index(prediction) else: return random.choice(range(len(choices))) if __name__ == "__main__": args = get_args() base_dir = args.base_dir split_indices = json.load(open(os.path.join(base_dir, "pid_splits.json")))[args.split] problems = json.load(open(os.path.join(base_dir, "problems.json"))) our_predictions = [json.loads(line) for line in open(args.our_result)] our_predictions = {pred['question_id']: pred for pred in our_predictions} split_problems = {idx: problems[idx] for idx in split_indices} requery_predictions = [json.loads(line) for line in open(args.requery_result)] requery_predictions = {pred['question_id']: pred for pred in requery_predictions} gpt4_predictions = json.load(open(args.gpt4_result))['outputs'] results = defaultdict(lambda: 0) sqa_results = {} sqa_results['acc'] = None sqa_results['correct'] = None sqa_results['count'] = None sqa_results['results'] = {} sqa_results['outputs'] = {} for prob_id, prob in split_problems.items(): if prob_id not in our_predictions: assert False if prob_id not in gpt4_predictions: assert False our_pred = our_predictions[prob_id]['text'] gpt4_pred = gpt4_predictions[prob_id] if prob_id not in requery_predictions: results['missing_requery'] += 1 requery_pred = "MISSING" else: requery_pred = requery_predictions[prob_id]['text'] pattern = re.compile(r'The answer is ([A-Z]).') our_res = pattern.findall(our_pred) if len(our_res) == 1: our_answer = our_res[0] # 'A', 'B', ... else: our_answer = "FAILED" requery_res = pattern.findall(requery_pred) if len(requery_res) == 1: requery_answer = requery_res[0] # 'A', 'B', ... else: requery_answer = "FAILED" gpt4_res = pattern.findall(gpt4_pred) if len(gpt4_res) == 1: gpt4_answer = gpt4_res[0] # 'A', 'B', ... else: gpt4_answer = "FAILED" our_pred_idx = get_pred_idx(our_answer, prob['choices'], args.options) gpt4_pred_idx = get_pred_idx(gpt4_answer, prob['choices'], args.options) requery_pred_idx = get_pred_idx(requery_answer, prob['choices'], args.options) results['total'] += 1 if gpt4_answer == 'FAILED': results['gpt4_failed'] += 1 if gpt4_pred_idx == prob['answer']: results['gpt4_correct'] += 1 if our_pred_idx == prob['answer']: results['gpt4_ourvisual_correct'] += 1 elif gpt4_pred_idx == prob['answer']: results['gpt4_correct'] += 1 results['gpt4_ourvisual_correct'] += 1 if our_pred_idx == prob['answer']: results['our_correct'] += 1 if requery_answer == 'FAILED': sqa_results['results'][prob_id] = our_pred_idx if our_pred_idx == prob['answer']: results['requery_correct'] += 1 else: sqa_results['results'][prob_id] = requery_pred_idx if requery_pred_idx == prob['answer']: results['requery_correct'] += 1 else: print(f""" Question ({args.options[prob['answer']]}): {our_predictions[prob_id]['prompt']} Our ({our_answer}): {our_pred} GPT-4 ({gpt4_answer}): {gpt4_pred} Requery ({requery_answer}): {requery_pred} print("=====================================") """) if gpt4_pred_idx == prob['answer'] or our_pred_idx == prob['answer']: results['correct_upperbound'] += 1 total = results['total'] print(f'Total: {total}, Our-Correct: {results["our_correct"]}, Accuracy: {results["our_correct"] / total * 100:.2f}%') print(f'Total: {total}, GPT-4-Correct: {results["gpt4_correct"]}, Accuracy: {results["gpt4_correct"] / total * 100:.2f}%') print(f'Total: {total}, GPT-4 NO-ANS (RANDOM): {results["gpt4_failed"]}, Percentage: {results["gpt4_failed"] / total * 100:.2f}%') print(f'Total: {total}, GPT-4-OursVisual-Correct: {results["gpt4_ourvisual_correct"]}, Accuracy: {results["gpt4_ourvisual_correct"] / total * 100:.2f}%') print(f'Total: {total}, Requery-Correct: {results["requery_correct"]}, Accuracy: {results["requery_correct"] / total * 100:.2f}%') print(f'Total: {total}, Correct upper: {results["correct_upperbound"]}, Accuracy: {results["correct_upperbound"] / total * 100:.2f}%') sqa_results['acc'] = results["requery_correct"] / total * 100 sqa_results['correct'] = results["requery_correct"] sqa_results['count'] = total with open(args.output_result, 'w') as f: json.dump(sqa_results, f, indent=2) ================================================ FILE: llava/eval/eval_textvqa.py ================================================ import os import argparse import json import re from llava.eval.m4c_evaluator import TextVQAAccuracyEvaluator def get_args(): parser = argparse.ArgumentParser() parser.add_argument('--annotation-file', type=str) parser.add_argument('--result-file', type=str) parser.add_argument('--result-dir', type=str) return parser.parse_args() def prompt_processor(prompt): if prompt.startswith('OCR tokens: '): pattern = r"Question: (.*?) Short answer:" match = re.search(pattern, prompt, re.DOTALL) question = match.group(1) elif 'Reference OCR token: ' in prompt and len(prompt.split('\n')) == 3: if prompt.startswith('Reference OCR token:'): question = prompt.split('\n')[1] else: question = prompt.split('\n')[0] elif len(prompt.split('\n')) == 2: question = prompt.split('\n')[0] else: assert False return question.lower() def eval_single(annotation_file, result_file): experiment_name = os.path.splitext(os.path.basename(result_file))[0] print(experiment_name) annotations = json.load(open(annotation_file))['data'] annotations = {(annotation['image_id'], annotation['question'].lower()): annotation for annotation in annotations} results = [json.loads(line) for line in open(result_file)] pred_list = [] for result in results: annotation = annotations[(result['question_id'], prompt_processor(result['prompt']))] pred_list.append({ "pred_answer": result['text'], "gt_answers": annotation['answers'], }) evaluator = TextVQAAccuracyEvaluator() print('Samples: {}\nAccuracy: {:.2f}%\n'.format(len(pred_list), 100. * evaluator.eval_pred_list(pred_list))) if __name__ == "__main__": args = get_args() if args.result_file is not None: eval_single(args.annotation_file, args.result_file) if args.result_dir is not None: for result_file in sorted(os.listdir(args.result_dir)): if not result_file.endswith('.jsonl'): print(f'Skipping {result_file}') continue eval_single(args.annotation_file, os.path.join(args.result_dir, result_file)) ================================================ FILE: llava/eval/generate_webpage_data_from_table.py ================================================ """Generate json file for webpage.""" import json import os import re # models = ['llama', 'alpaca', 'gpt35', 'bard'] models = ['vicuna'] def read_jsonl(path: str, key: str=None): data = [] with open(os.path.expanduser(path)) as f: for line in f: if not line: continue data.append(json.loads(line)) if key is not None: data.sort(key=lambda x: x[key]) data = {item[key]: item for item in data} return data def trim_hanging_lines(s: str, n: int) -> str: s = s.strip() for _ in range(n): s = s.split('\n', 1)[1].strip() return s if __name__ == '__main__': questions = read_jsonl('table/question.jsonl', key='question_id') # alpaca_answers = read_jsonl('table/answer/answer_alpaca-13b.jsonl', key='question_id') # bard_answers = read_jsonl('table/answer/answer_bard.jsonl', key='question_id') # gpt35_answers = read_jsonl('table/answer/answer_gpt35.jsonl', key='question_id') # llama_answers = read_jsonl('table/answer/answer_llama-13b.jsonl', key='question_id') vicuna_answers = read_jsonl('table/answer/answer_vicuna-13b.jsonl', key='question_id') ours_answers = read_jsonl('table/results/llama-13b-hf-alpaca.jsonl', key='question_id') review_vicuna = read_jsonl('table/review/review_vicuna-13b_llama-13b-hf-alpaca.jsonl', key='question_id') # review_alpaca = read_jsonl('table/review/review_alpaca-13b_vicuna-13b.jsonl', key='question_id') # review_bard = read_jsonl('table/review/review_bard_vicuna-13b.jsonl', key='question_id') # review_gpt35 = read_jsonl('table/review/review_gpt35_vicuna-13b.jsonl', key='question_id') # review_llama = read_jsonl('table/review/review_llama-13b_vicuna-13b.jsonl', key='question_id') records = [] for qid in questions.keys(): r = { 'id': qid, 'category': questions[qid]['category'], 'question': questions[qid]['text'], 'answers': { # 'alpaca': alpaca_answers[qid]['text'], # 'llama': llama_answers[qid]['text'], # 'bard': bard_answers[qid]['text'], # 'gpt35': gpt35_answers[qid]['text'], 'vicuna': vicuna_answers[qid]['text'], 'ours': ours_answers[qid]['text'], }, 'evaluations': { # 'alpaca': review_alpaca[qid]['text'], # 'llama': review_llama[qid]['text'], # 'bard': review_bard[qid]['text'], 'vicuna': review_vicuna[qid]['content'], # 'gpt35': review_gpt35[qid]['text'], }, 'scores': { 'vicuna': review_vicuna[qid]['tuple'], # 'alpaca': review_alpaca[qid]['score'], # 'llama': review_llama[qid]['score'], # 'bard': review_bard[qid]['score'], # 'gpt35': review_gpt35[qid]['score'], }, } # cleanup data cleaned_evals = {} for k, v in r['evaluations'].items(): v = v.strip() lines = v.split('\n') # trim the first line if it's a pair of numbers if re.match(r'\d+[, ]+\d+', lines[0]): lines = lines[1:] v = '\n'.join(lines) cleaned_evals[k] = v.replace('Assistant 1', "**Assistant 1**").replace('Assistant 2', '**Assistant 2**') r['evaluations'] = cleaned_evals records.append(r) # Reorder the records, this is optional for r in records: if r['id'] <= 20: r['id'] += 60 else: r['id'] -= 20 for r in records: if r['id'] <= 50: r['id'] += 10 elif 50 < r['id'] <= 60: r['id'] -= 50 for r in records: if r['id'] == 7: r['id'] = 1 elif r['id'] < 7: r['id'] += 1 records.sort(key=lambda x: x['id']) # Write to file with open('webpage/data.json', 'w') as f: json.dump({'questions': records, 'models': models}, f, indent=2) ================================================ FILE: llava/eval/m4c_evaluator.py ================================================ # Copyright (c) Facebook, Inc. and its affiliates. import re from tqdm import tqdm class EvalAIAnswerProcessor: """ Processes an answer similar to Eval AI copied from https://github.com/facebookresearch/mmf/blob/c46b3b3391275b4181567db80943473a89ab98ab/pythia/tasks/processors.py#L897 """ CONTRACTIONS = { "aint": "ain't", "arent": "aren't", "cant": "can't", "couldve": "could've", "couldnt": "couldn't", "couldn'tve": "couldn't've", "couldnt've": "couldn't've", "didnt": "didn't", "doesnt": "doesn't", "dont": "don't", "hadnt": "hadn't", "hadnt've": "hadn't've", "hadn'tve": "hadn't've", "hasnt": "hasn't", "havent": "haven't", "hed": "he'd", "hed've": "he'd've", "he'dve": "he'd've", "hes": "he's", "howd": "how'd", "howll": "how'll", "hows": "how's", "Id've": "I'd've", "I'dve": "I'd've", "Im": "I'm", "Ive": "I've", "isnt": "isn't", "itd": "it'd", "itd've": "it'd've", "it'dve": "it'd've", "itll": "it'll", "let's": "let's", "maam": "ma'am", "mightnt": "mightn't", "mightnt've": "mightn't've", "mightn'tve": "mightn't've", "mightve": "might've", "mustnt": "mustn't", "mustve": "must've", "neednt": "needn't", "notve": "not've", "oclock": "o'clock", "oughtnt": "oughtn't", "ow's'at": "'ow's'at", "'ows'at": "'ow's'at", "'ow'sat": "'ow's'at", "shant": "shan't", "shed've": "she'd've", "she'dve": "she'd've", "she's": "she's", "shouldve": "should've", "shouldnt": "shouldn't", "shouldnt've": "shouldn't've", "shouldn'tve": "shouldn't've", "somebody'd": "somebodyd", "somebodyd've": "somebody'd've", "somebody'dve": "somebody'd've", "somebodyll": "somebody'll", "somebodys": "somebody's", "someoned": "someone'd", "someoned've": "someone'd've", "someone'dve": "someone'd've", "someonell": "someone'll", "someones": "someone's", "somethingd": "something'd", "somethingd've": "something'd've", "something'dve": "something'd've", "somethingll": "something'll", "thats": "that's", "thered": "there'd", "thered've": "there'd've", "there'dve": "there'd've", "therere": "there're", "theres": "there's", "theyd": "they'd", "theyd've": "they'd've", "they'dve": "they'd've", "theyll": "they'll", "theyre": "they're", "theyve": "they've", "twas": "'twas", "wasnt": "wasn't", "wed've": "we'd've", "we'dve": "we'd've", "weve": "we've", "werent": "weren't", "whatll": "what'll", "whatre": "what're", "whats": "what's", "whatve": "what've", "whens": "when's", "whered": "where'd", "wheres": "where's", "whereve": "where've", "whod": "who'd", "whod've": "who'd've", "who'dve": "who'd've", "wholl": "who'll", "whos": "who's", "whove": "who've", "whyll": "why'll", "whyre": "why're", "whys": "why's", "wont": "won't", "wouldve": "would've", "wouldnt": "wouldn't", "wouldnt've": "wouldn't've", "wouldn'tve": "wouldn't've", "yall": "y'all", "yall'll": "y'all'll", "y'allll": "y'all'll", "yall'd've": "y'all'd've", "y'alld've": "y'all'd've", "y'all'dve": "y'all'd've", "youd": "you'd", "youd've": "you'd've", "you'dve": "you'd've", "youll": "you'll", "youre": "you're", "youve": "you've", } NUMBER_MAP = { "none": "0", "zero": "0", "one": "1", "two": "2", "three": "3", "four": "4", "five": "5", "six": "6", "seven": "7", "eight": "8", "nine": "9", "ten": "10", } ARTICLES = ["a", "an", "the"] PERIOD_STRIP = re.compile(r"(?!<=\d)(\.)(?!\d)") COMMA_STRIP = re.compile(r"(?<=\d)(\,)+(?=\d)") PUNCTUATIONS = [ ";", r"/", "[", "]", '"', "{", "}", "(", ")", "=", "+", "\\", "_", "-", ">", "<", "@", "`", ",", "?", "!", ] def __init__(self, *args, **kwargs): pass def word_tokenize(self, word): word = word.lower() word = word.replace(",", "").replace("?", "").replace("'s", " 's") return word.strip() def process_punctuation(self, in_text): out_text = in_text for p in self.PUNCTUATIONS: if (p + " " in in_text or " " + p in in_text) or ( re.search(self.COMMA_STRIP, in_text) is not None ): out_text = out_text.replace(p, "") else: out_text = out_text.replace(p, " ") out_text = self.PERIOD_STRIP.sub("", out_text, re.UNICODE) return out_text def process_digit_article(self, in_text): out_text = [] temp_text = in_text.lower().split() for word in temp_text: word = self.NUMBER_MAP.setdefault(word, word) if word not in self.ARTICLES: out_text.append(word) else: pass for word_id, word in enumerate(out_text): if word in self.CONTRACTIONS: out_text[word_id] = self.CONTRACTIONS[word] out_text = " ".join(out_text) return out_text def __call__(self, item): item = self.word_tokenize(item) item = item.replace("\n", " ").replace("\t", " ").strip() item = self.process_punctuation(item) item = self.process_digit_article(item) return item class TextVQAAccuracyEvaluator: def __init__(self): self.answer_processor = EvalAIAnswerProcessor() def _compute_answer_scores(self, raw_answers): """ compute the accuracy (soft score) of human answers """ answers = [self.answer_processor(a) for a in raw_answers] assert len(answers) == 10 gt_answers = list(enumerate(answers)) unique_answers = set(answers) unique_answer_scores = {} for unique_answer in unique_answers: accs = [] for gt_answer in gt_answers: other_answers = [item for item in gt_answers if item != gt_answer] matching_answers = [ item for item in other_answers if item[1] == unique_answer ] acc = min(1, float(len(matching_answers)) / 3) accs.append(acc) unique_answer_scores[unique_answer] = sum(accs) / len(accs) return unique_answer_scores def eval_pred_list(self, pred_list): pred_scores = [] for entry in tqdm(pred_list): pred_answer = self.answer_processor(entry["pred_answer"]) unique_answer_scores = self._compute_answer_scores(entry["gt_answers"]) score = unique_answer_scores.get(pred_answer, 0.0) pred_scores.append(score) accuracy = sum(pred_scores) / len(pred_scores) return accuracy class STVQAAccuracyEvaluator: def __init__(self): self.answer_processor = EvalAIAnswerProcessor() def eval_pred_list(self, pred_list): pred_scores = [] for entry in pred_list: pred_answer = self.answer_processor(entry["pred_answer"]) gts = [self.answer_processor(a) for a in entry["gt_answers"]] score = 1.0 if pred_answer in gts else 0.0 pred_scores.append(score) accuracy = sum(pred_scores) / len(pred_scores) return accuracy class STVQAANLSEvaluator: def __init__(self): import editdistance # install with `pip install editdistance` self.get_edit_distance = editdistance.eval def get_anls(self, s1, s2): s1 = s1.lower().strip() s2 = s2.lower().strip() iou = 1 - self.get_edit_distance(s1, s2) / max(len(s1), len(s2)) anls = iou if iou >= 0.5 else 0.0 return anls def eval_pred_list(self, pred_list): pred_scores = [] for entry in pred_list: anls = max( self.get_anls(entry["pred_answer"], gt) for gt in entry["gt_answers"] ) pred_scores.append(anls) accuracy = sum(pred_scores) / len(pred_scores) return accuracy class TextCapsBleu4Evaluator: def __init__(self): # The following script requires Java 1.8.0 and pycocotools installed. # The pycocoevalcap can be installed with pip as # pip install git+https://github.com/ronghanghu/coco-caption.git@python23 # Original pycocoevalcap code is at https://github.com/tylin/coco-caption # but has no python3 support yet. try: from pycocoevalcap.bleu.bleu import Bleu from pycocoevalcap.tokenizer.ptbtokenizer import PTBTokenizer except ModuleNotFoundError: print( "Please install pycocoevalcap module using " "pip install git+https://github.com/ronghanghu/coco-caption.git@python23" # noqa ) raise self.tokenizer = PTBTokenizer() self.scorer = Bleu(4) def eval_pred_list(self, pred_list): # Create reference and hypotheses captions. gts = {} res = {} for idx, entry in enumerate(pred_list): gts[idx] = [{"caption": a} for a in entry["gt_answers"]] res[idx] = [{"caption": entry["pred_answer"]}] gts = self.tokenizer.tokenize(gts) res = self.tokenizer.tokenize(res) score, _ = self.scorer.compute_score(gts, res) bleu4 = score[3] # score is (Bleu-1, Bleu-2, Bleu-3, Bleu-4) return bleu4 ================================================ FILE: llava/eval/model_qa.py ================================================ import argparse from transformers import AutoTokenizer, AutoModelForCausalLM, StoppingCriteria import torch import os import json from tqdm import tqdm import shortuuid from llava.conversation import default_conversation from llava.utils import disable_torch_init @torch.inference_mode() def eval_model(model_name, questions_file, answers_file): # Model disable_torch_init() model_name = os.path.expanduser(model_name) tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False) model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16).cuda() ques_file = open(os.path.expanduser(questions_file), "r") ans_file = open(os.path.expanduser(answers_file), "w") for i, line in enumerate(tqdm(ques_file)): idx = json.loads(line)["question_id"] qs = json.loads(line)["text"] cat = json.loads(line)["category"] conv = default_conversation.copy() conv.append_message(conv.roles[0], qs) prompt = conv.get_prompt() inputs = tokenizer([prompt]) input_ids = torch.as_tensor(inputs.input_ids).cuda() output_ids = model.generate( input_ids, do_sample=True, use_cache=True, temperature=0.7, max_new_tokens=1024,) outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0] try: index = outputs.index(conv.sep, len(prompt)) except ValueError: outputs += conv.sep index = outputs.index(conv.sep, len(prompt)) outputs = outputs[len(prompt) + len(conv.roles[1]) + 2:index].strip() ans_id = shortuuid.uuid() ans_file.write(json.dumps({"question_id": idx, "text": outputs, "answer_id": ans_id, "model_id": model_name, "metadata": {}}) + "\n") ans_file.flush() ans_file.close() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-name", type=str, default="facebook/opt-350m") parser.add_argument("--question-file", type=str, default="tables/question.jsonl") parser.add_argument("--answers-file", type=str, default="answer.jsonl") args = parser.parse_args() eval_model(args.model_name, args.question_file, args.answers_file) ================================================ FILE: llava/eval/model_vqa.py ================================================ import argparse import torch import os import json from tqdm import tqdm import shortuuid from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from llava.conversation import conv_templates, SeparatorStyle from llava.model.builder import load_pretrained_model from llava.utils import disable_torch_init from llava.mm_utils import tokenizer_image_token, process_images, get_model_name_from_path from PIL import Image import math def split_list(lst, n): """Split a list into n (roughly) equal-sized chunks""" chunk_size = math.ceil(len(lst) / n) # integer division return [lst[i:i+chunk_size] for i in range(0, len(lst), chunk_size)] def get_chunk(lst, n, k): chunks = split_list(lst, n) return chunks[k] def eval_model(args): # Model disable_torch_init() model_path = os.path.expanduser(args.model_path) model_name = get_model_name_from_path(model_path) tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, args.model_base, model_name) questions = [json.loads(q) for q in open(os.path.expanduser(args.question_file), "r")] questions = get_chunk(questions, args.num_chunks, args.chunk_idx) answers_file = os.path.expanduser(args.answers_file) os.makedirs(os.path.dirname(answers_file), exist_ok=True) ans_file = open(answers_file, "w") for line in tqdm(questions): idx = line["question_id"] image_file = line["image"] qs = line["text"] cur_prompt = qs if model.config.mm_use_im_start_end: qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + qs else: qs = DEFAULT_IMAGE_TOKEN + '\n' + qs conv = conv_templates[args.conv_mode].copy() conv.append_message(conv.roles[0], qs) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda() image = Image.open(os.path.join(args.image_folder, image_file)).convert('RGB') image_tensor = process_images([image], image_processor, model.config)[0] with torch.inference_mode(): output_ids = model.generate( input_ids, images=image_tensor.unsqueeze(0).half().cuda(), image_sizes=[image.size], do_sample=True if args.temperature > 0 else False, temperature=args.temperature, top_p=args.top_p, num_beams=args.num_beams, # no_repeat_ngram_size=3, max_new_tokens=1024, use_cache=True) outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip() ans_id = shortuuid.uuid() ans_file.write(json.dumps({"question_id": idx, "prompt": cur_prompt, "text": outputs, "answer_id": ans_id, "model_id": model_name, "metadata": {}}) + "\n") ans_file.flush() ans_file.close() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-path", type=str, default="facebook/opt-350m") parser.add_argument("--model-base", type=str, default=None) parser.add_argument("--image-folder", type=str, default="") parser.add_argument("--question-file", type=str, default="tables/question.jsonl") parser.add_argument("--answers-file", type=str, default="answer.jsonl") parser.add_argument("--conv-mode", type=str, default="llava_v1") parser.add_argument("--num-chunks", type=int, default=1) parser.add_argument("--chunk-idx", type=int, default=0) parser.add_argument("--temperature", type=float, default=0.2) parser.add_argument("--top_p", type=float, default=None) parser.add_argument("--num_beams", type=int, default=1) args = parser.parse_args() eval_model(args) ================================================ FILE: llava/eval/model_vqa_loader.py ================================================ import argparse import torch import os import json from tqdm import tqdm import shortuuid from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from llava.conversation import conv_templates, SeparatorStyle from llava.model.builder import load_pretrained_model from llava.utils import disable_torch_init from llava.mm_utils import tokenizer_image_token, process_images, get_model_name_from_path from torch.utils.data import Dataset, DataLoader from PIL import Image import math def split_list(lst, n): """Split a list into n (roughly) equal-sized chunks""" chunk_size = math.ceil(len(lst) / n) # integer division return [lst[i:i+chunk_size] for i in range(0, len(lst), chunk_size)] def get_chunk(lst, n, k): chunks = split_list(lst, n) return chunks[k] # Custom dataset class class CustomDataset(Dataset): def __init__(self, questions, image_folder, tokenizer, image_processor, model_config): self.questions = questions self.image_folder = image_folder self.tokenizer = tokenizer self.image_processor = image_processor self.model_config = model_config def __getitem__(self, index): line = self.questions[index] image_file = line["image"] qs = line["text"] if self.model_config.mm_use_im_start_end: qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + qs else: qs = DEFAULT_IMAGE_TOKEN + '\n' + qs conv = conv_templates[args.conv_mode].copy() conv.append_message(conv.roles[0], qs) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() image = Image.open(os.path.join(self.image_folder, image_file)).convert('RGB') image_tensor = process_images([image], self.image_processor, self.model_config)[0] input_ids = tokenizer_image_token(prompt, self.tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt') return input_ids, image_tensor, image.size def __len__(self): return len(self.questions) def collate_fn(batch): input_ids, image_tensors, image_sizes = zip(*batch) input_ids = torch.stack(input_ids, dim=0) image_tensors = torch.stack(image_tensors, dim=0) return input_ids, image_tensors, image_sizes # DataLoader def create_data_loader(questions, image_folder, tokenizer, image_processor, model_config, batch_size=1, num_workers=4): assert batch_size == 1, "batch_size must be 1" dataset = CustomDataset(questions, image_folder, tokenizer, image_processor, model_config) data_loader = DataLoader(dataset, batch_size=batch_size, num_workers=num_workers, shuffle=False, collate_fn=collate_fn) return data_loader def eval_model(args): # Model disable_torch_init() model_path = os.path.expanduser(args.model_path) model_name = get_model_name_from_path(model_path) tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, args.model_base, model_name) questions = [json.loads(q) for q in open(os.path.expanduser(args.question_file), "r")] questions = get_chunk(questions, args.num_chunks, args.chunk_idx) answers_file = os.path.expanduser(args.answers_file) os.makedirs(os.path.dirname(answers_file), exist_ok=True) ans_file = open(answers_file, "w") if 'plain' in model_name and 'finetune' not in model_name.lower() and 'mmtag' not in args.conv_mode: args.conv_mode = args.conv_mode + '_mmtag' print(f'It seems that this is a plain model, but it is not using a mmtag prompt, auto switching to {args.conv_mode}.') data_loader = create_data_loader(questions, args.image_folder, tokenizer, image_processor, model.config) for (input_ids, image_tensor, image_sizes), line in tqdm(zip(data_loader, questions), total=len(questions)): idx = line["question_id"] cur_prompt = line["text"] input_ids = input_ids.to(device='cuda', non_blocking=True) with torch.inference_mode(): output_ids = model.generate( input_ids, images=image_tensor.to(dtype=torch.float16, device='cuda', non_blocking=True), image_sizes=image_sizes, do_sample=True if args.temperature > 0 else False, temperature=args.temperature, top_p=args.top_p, num_beams=args.num_beams, max_new_tokens=args.max_new_tokens, use_cache=True) outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip() ans_id = shortuuid.uuid() ans_file.write(json.dumps({"question_id": idx, "prompt": cur_prompt, "text": outputs, "answer_id": ans_id, "model_id": model_name, "metadata": {}}) + "\n") # ans_file.flush() ans_file.close() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-path", type=str, default="facebook/opt-350m") parser.add_argument("--model-base", type=str, default=None) parser.add_argument("--image-folder", type=str, default="") parser.add_argument("--question-file", type=str, default="tables/question.jsonl") parser.add_argument("--answers-file", type=str, default="answer.jsonl") parser.add_argument("--conv-mode", type=str, default="llava_v1") parser.add_argument("--num-chunks", type=int, default=1) parser.add_argument("--chunk-idx", type=int, default=0) parser.add_argument("--temperature", type=float, default=0.2) parser.add_argument("--top_p", type=float, default=None) parser.add_argument("--num_beams", type=int, default=1) parser.add_argument("--max_new_tokens", type=int, default=128) args = parser.parse_args() eval_model(args) ================================================ FILE: llava/eval/model_vqa_mmbench.py ================================================ import argparse import torch import os import json import pandas as pd from tqdm import tqdm import shortuuid from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from llava.conversation import conv_templates, SeparatorStyle from llava.model.builder import load_pretrained_model from llava.utils import disable_torch_init from llava.mm_utils import tokenizer_image_token, process_images, load_image_from_base64, get_model_name_from_path from PIL import Image import math all_options = ['A', 'B', 'C', 'D'] def split_list(lst, n): """Split a list into n (roughly) equal-sized chunks""" chunk_size = math.ceil(len(lst) / n) # integer division return [lst[i:i+chunk_size] for i in range(0, len(lst), chunk_size)] def get_chunk(lst, n, k): chunks = split_list(lst, n) return chunks[k] def is_none(value): if value is None: return True if type(value) is float and math.isnan(value): return True if type(value) is str and value.lower() == 'nan': return True if type(value) is str and value.lower() == 'none': return True return False def get_options(row, options): parsed_options = [] for option in options: option_value = row[option] if is_none(option_value): break parsed_options.append(option_value) return parsed_options def eval_model(args): # Model disable_torch_init() model_path = os.path.expanduser(args.model_path) model_name = get_model_name_from_path(model_path) tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, args.model_base, model_name) questions = pd.read_table(os.path.expanduser(args.question_file)) questions = get_chunk(questions, args.num_chunks, args.chunk_idx) answers_file = os.path.expanduser(args.answers_file) os.makedirs(os.path.dirname(answers_file), exist_ok=True) ans_file = open(answers_file, "w") if 'plain' in model_name and 'finetune' not in model_name.lower() and 'mmtag' not in args.conv_mode: args.conv_mode = args.conv_mode + '_mmtag' print(f'It seems that this is a plain model, but it is not using a mmtag prompt, auto switching to {args.conv_mode}.') for index, row in tqdm(questions.iterrows(), total=len(questions)): options = get_options(row, all_options) cur_option_char = all_options[:len(options)] if args.all_rounds: num_rounds = len(options) else: num_rounds = 1 for round_idx in range(num_rounds): idx = row['index'] question = row['question'] hint = row['hint'] image = load_image_from_base64(row['image']) if not is_none(hint): question = hint + '\n' + question for option_char, option in zip(all_options[:len(options)], options): question = question + '\n' + option_char + '. ' + option qs = cur_prompt = question if model.config.mm_use_im_start_end: qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + qs else: qs = DEFAULT_IMAGE_TOKEN + '\n' + qs if args.single_pred_prompt: if args.lang == 'cn': qs = qs + '\n' + "请直接回答选项字母。" else: qs = qs + '\n' + "Answer with the option's letter from the given choices directly." conv = conv_templates[args.conv_mode].copy() conv.append_message(conv.roles[0], qs) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda() image_tensor = process_images([image], image_processor, model.config)[0] with torch.inference_mode(): output_ids = model.generate( input_ids, images=image_tensor.unsqueeze(0).half().cuda(), image_sizes=[image.size], do_sample=True if args.temperature > 0 else False, temperature=args.temperature, top_p=args.top_p, num_beams=args.num_beams, # no_repeat_ngram_size=3, max_new_tokens=1024, use_cache=True) outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip() ans_id = shortuuid.uuid() ans_file.write(json.dumps({"question_id": idx, "round_id": round_idx, "prompt": cur_prompt, "text": outputs, "options": options, "option_char": cur_option_char, "answer_id": ans_id, "model_id": model_name, "metadata": {}}) + "\n") ans_file.flush() # rotate options options = options[1:] + options[:1] cur_option_char = cur_option_char[1:] + cur_option_char[:1] ans_file.close() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-path", type=str, default="facebook/opt-350m") parser.add_argument("--model-base", type=str, default=None) parser.add_argument("--image-folder", type=str, default="") parser.add_argument("--question-file", type=str, default="tables/question.jsonl") parser.add_argument("--answers-file", type=str, default="answer.jsonl") parser.add_argument("--conv-mode", type=str, default="llava_v1") parser.add_argument("--num-chunks", type=int, default=1) parser.add_argument("--chunk-idx", type=int, default=0) parser.add_argument("--temperature", type=float, default=0.2) parser.add_argument("--top_p", type=float, default=None) parser.add_argument("--num_beams", type=int, default=1) parser.add_argument("--all-rounds", action="store_true") parser.add_argument("--single-pred-prompt", action="store_true") parser.add_argument("--lang", type=str, default="en") args = parser.parse_args() eval_model(args) ================================================ FILE: llava/eval/model_vqa_science.py ================================================ import argparse import torch import os import json from tqdm import tqdm import shortuuid from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from llava.conversation import conv_templates, SeparatorStyle from llava.model.builder import load_pretrained_model from llava.utils import disable_torch_init from llava.mm_utils import tokenizer_image_token, process_images, get_model_name_from_path from PIL import Image import math def split_list(lst, n): """Split a list into n (roughly) equal-sized chunks""" chunk_size = math.ceil(len(lst) / n) # integer division return [lst[i:i+chunk_size] for i in range(0, len(lst), chunk_size)] def get_chunk(lst, n, k): chunks = split_list(lst, n) return chunks[k] def eval_model(args): # Model disable_torch_init() model_path = os.path.expanduser(args.model_path) model_name = get_model_name_from_path(model_path) tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, args.model_base, model_name) questions = json.load(open(os.path.expanduser(args.question_file), "r")) questions = get_chunk(questions, args.num_chunks, args.chunk_idx) answers_file = os.path.expanduser(args.answers_file) os.makedirs(os.path.dirname(answers_file), exist_ok=True) ans_file = open(answers_file, "w") for i, line in enumerate(tqdm(questions)): idx = line["id"] question = line['conversations'][0] qs = question['value'].replace('', '').strip() cur_prompt = qs if 'image' in line: image_file = line["image"] image = Image.open(os.path.join(args.image_folder, image_file)) image_tensor = process_images([image], image_processor, model.config)[0] images = image_tensor.unsqueeze(0).half().cuda() image_sizes = [image.size] if getattr(model.config, 'mm_use_im_start_end', False): qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + qs else: qs = DEFAULT_IMAGE_TOKEN + '\n' + qs cur_prompt = '' + '\n' + cur_prompt else: images = None image_sizes = None if args.single_pred_prompt: qs = qs + '\n' + "Answer with the option's letter from the given choices directly." cur_prompt = cur_prompt + '\n' + "Answer with the option's letter from the given choices directly." conv = conv_templates[args.conv_mode].copy() conv.append_message(conv.roles[0], qs) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda() with torch.inference_mode(): output_ids = model.generate( input_ids, images=images, image_sizes=image_sizes, do_sample=True if args.temperature > 0 else False, temperature=args.temperature, max_new_tokens=1024, use_cache=True, ) outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip() ans_id = shortuuid.uuid() ans_file.write(json.dumps({"question_id": idx, "prompt": cur_prompt, "text": outputs, "answer_id": ans_id, "model_id": model_name, "metadata": {}}) + "\n") ans_file.flush() ans_file.close() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-path", type=str, default="facebook/opt-350m") parser.add_argument("--model-base", type=str, default=None) parser.add_argument("--image-folder", type=str, default="") parser.add_argument("--question-file", type=str, default="tables/question.json") parser.add_argument("--answers-file", type=str, default="answer.jsonl") parser.add_argument("--conv-mode", type=str, default="llava_v0") parser.add_argument("--num-chunks", type=int, default=1) parser.add_argument("--chunk-idx", type=int, default=0) parser.add_argument("--temperature", type=float, default=0.2) parser.add_argument("--answer-prompter", action="store_true") parser.add_argument("--single-pred-prompt", action="store_true") args = parser.parse_args() eval_model(args) ================================================ FILE: llava/eval/qa_baseline_gpt35.py ================================================ """Generate answers with GPT-3.5""" # Note: you need to be using OpenAI Python v0.27.0 for the code below to work import argparse import json import os import time import concurrent.futures import openai import tqdm import shortuuid MODEL = 'gpt-3.5-turbo' MODEL_ID = 'gpt-3.5-turbo:20230327' def get_answer(question_id: int, question: str, max_tokens: int): ans = { 'answer_id': shortuuid.uuid(), 'question_id': question_id, 'model_id': MODEL_ID, } for _ in range(3): try: response = openai.ChatCompletion.create( model=MODEL, messages=[{ 'role': 'system', 'content': 'You are a helpful assistant.' }, { 'role': 'user', 'content': question, }], max_tokens=max_tokens, ) ans['text'] = response['choices'][0]['message']['content'] return ans except Exception as e: print('[ERROR]', e) ans['text'] = '#ERROR#' time.sleep(1) return ans if __name__ == '__main__': parser = argparse.ArgumentParser(description='ChatGPT answer generation.') parser.add_argument('-q', '--question') parser.add_argument('-o', '--output') parser.add_argument('--max-tokens', type=int, default=1024, help='maximum number of tokens produced in the output') args = parser.parse_args() questions_dict = {} with open(os.path.expanduser(args.question)) as f: for line in f: if not line: continue q = json.loads(line) questions_dict[q['question_id']] = q['text'] answers = [] with concurrent.futures.ThreadPoolExecutor(max_workers=32) as executor: futures = [] for qid, question in questions_dict.items(): future = executor.submit(get_answer, qid, question, args.max_tokens) futures.append(future) for future in tqdm.tqdm(concurrent.futures.as_completed(futures), total=len(futures)): answers.append(future.result()) answers.sort(key=lambda x: x['question_id']) with open(os.path.expanduser(args.output), 'w') as f: table = [json.dumps(ans) for ans in answers] f.write('\n'.join(table)) ================================================ FILE: llava/eval/run_llava.py ================================================ import argparse import torch from llava.constants import ( IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IMAGE_PLACEHOLDER, ) from llava.conversation import conv_templates, SeparatorStyle from llava.model.builder import load_pretrained_model from llava.utils import disable_torch_init from llava.mm_utils import ( process_images, tokenizer_image_token, get_model_name_from_path, ) from PIL import Image import requests from PIL import Image from io import BytesIO import re def image_parser(args): out = args.image_file.split(args.sep) return out def load_image(image_file): if image_file.startswith("http") or image_file.startswith("https"): response = requests.get(image_file) image = Image.open(BytesIO(response.content)).convert("RGB") else: image = Image.open(image_file).convert("RGB") return image def load_images(image_files): out = [] for image_file in image_files: image = load_image(image_file) out.append(image) return out def eval_model(args): # Model disable_torch_init() model_name = get_model_name_from_path(args.model_path) tokenizer, model, image_processor, context_len = load_pretrained_model( args.model_path, args.model_base, model_name ) qs = args.query image_token_se = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN if IMAGE_PLACEHOLDER in qs: if model.config.mm_use_im_start_end: qs = re.sub(IMAGE_PLACEHOLDER, image_token_se, qs) else: qs = re.sub(IMAGE_PLACEHOLDER, DEFAULT_IMAGE_TOKEN, qs) else: if model.config.mm_use_im_start_end: qs = image_token_se + "\n" + qs else: qs = DEFAULT_IMAGE_TOKEN + "\n" + qs if "llama-2" in model_name.lower(): conv_mode = "llava_llama_2" elif "mistral" in model_name.lower(): conv_mode = "mistral_instruct" elif "v1.6-34b" in model_name.lower(): conv_mode = "chatml_direct" elif "v1" in model_name.lower(): conv_mode = "llava_v1" elif "mpt" in model_name.lower(): conv_mode = "mpt" else: conv_mode = "llava_v0" if args.conv_mode is not None and conv_mode != args.conv_mode: print( "[WARNING] the auto inferred conversation mode is {}, while `--conv-mode` is {}, using {}".format( conv_mode, args.conv_mode, args.conv_mode ) ) else: args.conv_mode = conv_mode conv = conv_templates[args.conv_mode].copy() conv.append_message(conv.roles[0], qs) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() image_files = image_parser(args) images = load_images(image_files) image_sizes = [x.size for x in images] images_tensor = process_images( images, image_processor, model.config ).to(model.device, dtype=torch.float16) input_ids = ( tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt") .unsqueeze(0) .cuda() ) with torch.inference_mode(): output_ids = model.generate( input_ids, images=images_tensor, image_sizes=image_sizes, do_sample=True if args.temperature > 0 else False, temperature=args.temperature, top_p=args.top_p, num_beams=args.num_beams, max_new_tokens=args.max_new_tokens, use_cache=True, ) outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip() print(outputs) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-path", type=str, default="facebook/opt-350m") parser.add_argument("--model-base", type=str, default=None) parser.add_argument("--image-file", type=str, required=True) parser.add_argument("--query", type=str, required=True) parser.add_argument("--conv-mode", type=str, default=None) parser.add_argument("--sep", type=str, default=",") parser.add_argument("--temperature", type=float, default=0.2) parser.add_argument("--top_p", type=float, default=None) parser.add_argument("--num_beams", type=int, default=1) parser.add_argument("--max_new_tokens", type=int, default=512) args = parser.parse_args() eval_model(args) ================================================ FILE: llava/eval/summarize_gpt_review.py ================================================ import json import os from collections import defaultdict import numpy as np import argparse def parse_args(): parser = argparse.ArgumentParser(description='ChatGPT-based QA evaluation.') parser.add_argument('-d', '--dir', default=None) parser.add_argument('-v', '--version', default=None) parser.add_argument('-s', '--select', nargs='*', default=None) parser.add_argument('-f', '--files', nargs='*', default=[]) parser.add_argument('-i', '--ignore', nargs='*', default=[]) return parser.parse_args() if __name__ == '__main__': args = parse_args() if args.ignore is not None: args.ignore = [int(x) for x in args.ignore] if len(args.files) > 0: review_files = args.files else: review_files = [x for x in os.listdir(args.dir) if x.endswith('.jsonl') and (x.startswith('gpt4_text') or x.startswith('reviews_') or x.startswith('review_') or 'review' in args.dir)] for review_file in sorted(review_files): config = os.path.basename(review_file).replace('gpt4_text_', '').replace('.jsonl', '') if args.select is not None and any(x not in config for x in args.select): continue if '0613' in config: version = '0613' else: version = '0314' if args.version is not None and args.version != version: continue scores = defaultdict(list) print(config) with open(os.path.join(args.dir, review_file) if args.dir is not None else review_file) as f: for review_str in f: review = json.loads(review_str) if review['question_id'] in args.ignore: continue if 'category' in review: scores[review['category']].append(review['tuple']) scores['all'].append(review['tuple']) else: if 'tuple' in review: scores['all'].append(review['tuple']) else: scores['all'].append(review['score']) for k, v in sorted(scores.items()): stats = np.asarray(v).mean(0).tolist() stats = [round(x, 3) for x in stats] # print(k, stats, round(stats[1]/stats[0]*100, 1)) print(k, round(stats[1]/stats[0]*100, 1), round(stats[0] * 10, 1), round(stats[1] * 10, 1)) print('=================================') ================================================ FILE: llava/eval/webpage/index.html ================================================ Who's GPT-4's favorite? Battles between State-of-the-Art Chatbots

Who's GPT-4's favorite? Battles between State-of-the-Art Chatbots

other logo
vicuna logo
Assistant #2 (Vicuna, our model)
GPT-4 Evaluation
This website is co-authored with GPT-4.
================================================ FILE: llava/eval/webpage/script.js ================================================ // Description: Script for the evaluation webpage. let currentQuestionIndex = 1; // Store the model name mapping for later use. modelNameMapping = { "gpt35": "ChatGPT-3.5", "gpt4": "GPT-4", "alpaca": "Alpaca-13b", "vicuna": "Vicuna-13b", "llama": "LLaMA-13b", "bard": "Bard", }; modelFigureMapping = { "vicuna": "figures/vicuna.jpeg", // Image from: https://commons.wikimedia.org/wiki/File:ChatGPT_logo.svg "gpt35": "figures/chatgpt.svg", // Image from: https://www.reddit.com/r/logodesign/comments/1128aat/google_ai_bard_logo_design/ "bard": "figures/bard.jpg", // Image from: https://crfm.stanford.edu/2023/03/13/alpaca.html "alpaca": "figures/alpaca.png", // Image adapted from https://commons.wikimedia.org/wiki/File:Llama_on_Machu_Picchu.jpg "llama": "figures/llama.jpg", } // Store the question data in a mapping for later use. questionMapping = {}; // Store the question ids in a mapping for later use. categoryMapping = {}; // Store the number of questions for later use. questionsCount = 0; function text2Markdown(text) { // Normalize the text for markdown rendering. text = text.trim().replaceAll('\n\n', '\n').replaceAll('\n', '\n\n'); return marked.parse(text); } function capitalizeFirstChar(str) { if (!str || str.length === 0) { return str; } return str.charAt(0).toUpperCase() + str.slice(1); } function updateQuestionSelect(question_id) { const select = document.getElementById('question-select'); // Clear the question select. select.innerHTML = ''; // Populate the question select. category = questionMapping[question_id].category; categoryMapping[category].forEach(question_id => { const question = questionMapping[question_id]; const option = document.createElement('option'); option.value = question_id; option.textContent = 'Q' + question_id.toString() + ': ' + question.question; select.appendChild(option); }); select.value = question_id; } function updateModelSelect() { const select = document.getElementById('model-select'); img_path = modelFigureMapping[select.value]; document.getElementById('other-model-figure').src = img_path; } function populateModels(models) { const select = document.getElementById('model-select'); models.forEach(model => { const option = document.createElement('option'); option.value = model; option.textContent = modelNameMapping[model]; select.appendChild(option); }); updateModelSelect(); } function populateQuestions(questions) { const category_select = document.getElementById('category-select'); questionsCount = questions.length; questions.forEach(question => { const option = document.createElement('option'); // Store the question data in a mapping for later use. questionMapping[question.id] = { category: question.category, question: question.question, answers: question.answers, evaluations: question.evaluations, scores: question.scores, }; // Store the question id in the category mapping. if (question.category in categoryMapping) { categoryMapping[question.category].push(question.id); } else { categoryMapping[question.category] = [question.id]; const category_option = document.createElement('option'); category_option.value = question.category; category_option.textContent = capitalizeFirstChar(question.category); category_select.appendChild(category_option); } }); // Set the default category. updateQuestionSelect(currentQuestionIndex); } function displayQuestion(index) { const question = questionMapping[index].question; document.getElementById('selected-question').innerHTML = text2Markdown('**Question:** ' + question); displayAnswers(index); } function displayAnswers(index) { const question = questionMapping[index]; const otherModel = document.getElementById('model-select').value; // render the answers with markdown document.getElementById('other-model-answer').innerHTML = text2Markdown(question.answers[otherModel]); document.getElementById('our-model-answer').innerHTML = text2Markdown(question.answers.vicuna); // Display evaluation score = question.scores[otherModel]; score_text = modelNameMapping[otherModel] + " " + score[0] + "/10, Vicuna-13b " + score[1] + "/10"; document.getElementById('evaluation-header').textContent = "GPT-4 Evaluation" + " (Score: " + score_text + ")"; document.getElementById('evaluation-result').innerHTML = text2Markdown(question.evaluations[otherModel]); // Update model names let assistant1_title = "Assistant #1"; // (" + modelNameMapping[otherModel] + ")"; let assistant2_title = "Assistant #2 (Vicuna-13b, our model)"; // Update scores/labels. let assistant1_score_label = score[0].toString() + '/10'; let assistant2_score_label = score[1].toString() + '/10'; const colorRed ='#fa9'; // '#eb978d'; // const colorGreen = '#c9f2c9'; const colorBlue = '#8ef'; // '#71dbf9'; const colorYellow = '#fe7'; // '#fada57'; let otherModelHeaderColor = ''; let ourModelHeaderColor = ''; // Update the winner. if (score[0] == score[1]) { assistant1_title = '🏆 ' + assistant1_title; assistant1_score_label = '🏆 ' + assistant1_score_label; assistant2_title = '🏆 ' + assistant2_title; assistant2_score_label = '🏆 ' + assistant2_score_label; otherModelHeaderColor = colorYellow; ourModelHeaderColor = colorYellow; } else if (score[0] > score[1]) { assistant1_title = '🏆 ' + assistant1_title; assistant1_score_label = '🏆 ' + assistant1_score_label; otherModelHeaderColor = colorBlue; ourModelHeaderColor = colorRed; } else if (score[0] < score[1]) { assistant2_title = '🏆 ' + assistant2_title; assistant2_score_label = '🏆 ' + assistant2_score_label; otherModelHeaderColor = colorRed; ourModelHeaderColor = colorBlue; } document.getElementById('other-model-header-bg').style.backgroundColor = otherModelHeaderColor; document.getElementById('our-model-header').style.backgroundColor = ourModelHeaderColor; document.getElementById('other-model-header').textContent = assistant1_title; document.getElementById('our-model-header').textContent = assistant2_title; document.getElementById('other-score-label').textContent = assistant1_score_label; document.getElementById('our-score-label').textContent = assistant2_score_label; // Update expand buttons visibility for both cards after displaying answers // Reset the expanded state and update expand buttons visibility for both cards after displaying answers document.querySelectorAll('.expandable-card').forEach(card => { card.classList.remove('expanded'); updateExpandButtonVisibility(card); const expandBtn = card.querySelector('.expand-btn'); expandBtn.innerHTML = 'keyboard_arrow_down Show more'; // .textContent = 'Show more'; }); } document.getElementById('question-select').addEventListener('change', e => { currentQuestionIndex = parseInt(e.target.value); displayQuestion(currentQuestionIndex); }); document.getElementById('category-select').addEventListener('change', e => { let currentCategory = e.target.value; const questionIds = categoryMapping[currentCategory]; currentQuestionIndex = questionIds[0]; updateQuestionSelect(currentQuestionIndex); displayQuestion(currentQuestionIndex); }); // Update expand buttons whenever the model is changed document.getElementById('model-select').addEventListener('change', () => { displayAnswers(currentQuestionIndex); document.querySelectorAll('.expandable-card').forEach(card => { updateExpandButtonVisibility(card); }); updateModelSelect(); }); function switchQuestionAndCategory() { document.getElementById('question-select').value = currentQuestionIndex; old_category = document.getElementById('category-select').value; new_category = questionMapping[currentQuestionIndex].category; if (old_category != new_category) { document.getElementById('category-select').value = new_category; updateQuestionSelect(currentQuestionIndex); } displayQuestion(currentQuestionIndex); } document.getElementById('prev-question').addEventListener('click', () => { // Question index starts from 1. currentQuestionIndex = Math.max(1, currentQuestionIndex - 1); switchQuestionAndCategory(); }); document.getElementById('next-question').addEventListener('click', () => { // Question index starts from 1. currentQuestionIndex = Math.min(questionsCount, currentQuestionIndex + 1); switchQuestionAndCategory(); }); function updateExpandButtonVisibility(card) { const cardTextContainer = card.querySelector('.card-text-container'); const expandBtn = card.querySelector('.expand-btn'); if (cardTextContainer.scrollHeight > cardTextContainer.offsetHeight) { expandBtn.style.display = 'flex'; } else { expandBtn.style.display = 'none'; card.classList.add('expanded'); } } document.querySelectorAll('.expand-btn').forEach(btn => { btn.addEventListener('click', e => { const card = e.target.closest('.expandable-card'); card.classList.toggle('expanded'); const more = 'keyboard_arrow_down Show more'; const less = 'keyboard_arrow_up Show less'; e.target.innerHTML = card.classList.contains('expanded') ? less : more; }); }); ================================================ FILE: llava/eval/webpage/styles.css ================================================ body { font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; background-color: #f8f9fa; } .navbar-dark .navbar-nav .nav-link { color: #f1cf68; font-size: 1.1rem; padding: 0.5rem 0.6rem; } .card-header { font-weight: bold; } .card { box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1); transition: 0.3s; } .card:hover { box-shadow: 0 8px 16px rgba(0, 0, 0, 0.2); } button { transition: background-color 0.3s; } button:hover { background-color: #007bff; } @media (max-width: 767px) { .form-row .form-group { margin-bottom: 10px; } } /* Extra styles */ .expandable-card .card-text-container { max-height: 200px; overflow-y: hidden; position: relative; } .expandable-card.expanded .card-text-container { max-height: none; } .expand-btn { position: relative; display: none; background-color: rgba(255, 255, 255, 0.8); color: #510c75; border-color: transparent; } .expand-btn:hover { background-color: rgba(200, 200, 200, 0.8); text-decoration: none; border-color: transparent; color: #510c75; } .expand-btn:focus { outline: none; text-decoration: none; } .expandable-card:not(.expanded) .card-text-container:after { content: ""; position: absolute; bottom: 0; left: 0; width: 100%; height: 90px; background: linear-gradient(rgba(255, 255, 255, 0.2), rgba(255, 255, 255, 1)); } .expandable-card:not(.expanded) .expand-btn { margin-top: -40px; } .card-body { padding-bottom: 5px; } .vertical-flex-layout { justify-content: center; align-items: center; height: 100%; display: flex; flex-direction: column; gap: 5px; } .figure-img { max-width: 100%; height: auto; } .adjustable-font-size { font-size: calc(0.5rem + 2vw); } ================================================ FILE: llava/mm_utils.py ================================================ from PIL import Image from io import BytesIO import base64 import torch import math import ast from transformers import StoppingCriteria from llava.constants import IMAGE_TOKEN_INDEX def select_best_resolution(original_size, possible_resolutions): """ Selects the best resolution from a list of possible resolutions based on the original size. Args: original_size (tuple): The original size of the image in the format (width, height). possible_resolutions (list): A list of possible resolutions in the format [(width1, height1), (width2, height2), ...]. Returns: tuple: The best fit resolution in the format (width, height). """ original_width, original_height = original_size best_fit = None max_effective_resolution = 0 min_wasted_resolution = float('inf') for width, height in possible_resolutions: scale = min(width / original_width, height / original_height) downscaled_width, downscaled_height = int(original_width * scale), int(original_height * scale) effective_resolution = min(downscaled_width * downscaled_height, original_width * original_height) wasted_resolution = (width * height) - effective_resolution if effective_resolution > max_effective_resolution or (effective_resolution == max_effective_resolution and wasted_resolution < min_wasted_resolution): max_effective_resolution = effective_resolution min_wasted_resolution = wasted_resolution best_fit = (width, height) return best_fit def resize_and_pad_image(image, target_resolution): """ Resize and pad an image to a target resolution while maintaining aspect ratio. Args: image (PIL.Image.Image): The input image. target_resolution (tuple): The target resolution (width, height) of the image. Returns: PIL.Image.Image: The resized and padded image. """ original_width, original_height = image.size target_width, target_height = target_resolution scale_w = target_width / original_width scale_h = target_height / original_height if scale_w < scale_h: new_width = target_width new_height = min(math.ceil(original_height * scale_w), target_height) else: new_height = target_height new_width = min(math.ceil(original_width * scale_h), target_width) # Resize the image resized_image = image.resize((new_width, new_height)) new_image = Image.new('RGB', (target_width, target_height), (0, 0, 0)) paste_x = (target_width - new_width) // 2 paste_y = (target_height - new_height) // 2 new_image.paste(resized_image, (paste_x, paste_y)) return new_image def divide_to_patches(image, patch_size): """ Divides an image into patches of a specified size. Args: image (PIL.Image.Image): The input image. patch_size (int): The size of each patch. Returns: list: A list of PIL.Image.Image objects representing the patches. """ patches = [] width, height = image.size for i in range(0, height, patch_size): for j in range(0, width, patch_size): box = (j, i, j + patch_size, i + patch_size) patch = image.crop(box) patches.append(patch) return patches def get_anyres_image_grid_shape(image_size, grid_pinpoints, patch_size): """ Calculate the shape of the image patch grid after the preprocessing for images of any resolution. Args: image_size (tuple): The size of the input image in the format (width, height). grid_pinpoints (str): A string representation of a list of possible resolutions. patch_size (int): The size of each image patch. Returns: tuple: The shape of the image patch grid in the format (width, height). """ if type(grid_pinpoints) is list: possible_resolutions = grid_pinpoints else: possible_resolutions = ast.literal_eval(grid_pinpoints) width, height = select_best_resolution(image_size, possible_resolutions) return width // patch_size, height // patch_size def process_anyres_image(image, processor, grid_pinpoints): """ Process an image with variable resolutions. Args: image (PIL.Image.Image): The input image to be processed. processor: The image processor object. grid_pinpoints (str): A string representation of a list of possible resolutions. Returns: torch.Tensor: A tensor containing the processed image patches. """ if type(grid_pinpoints) is list: possible_resolutions = grid_pinpoints else: possible_resolutions = ast.literal_eval(grid_pinpoints) best_resolution = select_best_resolution(image.size, possible_resolutions) image_padded = resize_and_pad_image(image, best_resolution) patches = divide_to_patches(image_padded, processor.crop_size['height']) image_original_resize = image.resize((processor.size['shortest_edge'], processor.size['shortest_edge'])) image_patches = [image_original_resize] + patches image_patches = [processor.preprocess(image_patch, return_tensors='pt')['pixel_values'][0] for image_patch in image_patches] return torch.stack(image_patches, dim=0) def load_image_from_base64(image): return Image.open(BytesIO(base64.b64decode(image))) def expand2square(pil_img, background_color): width, height = pil_img.size if width == height: return pil_img elif width > height: result = Image.new(pil_img.mode, (width, width), background_color) result.paste(pil_img, (0, (width - height) // 2)) return result else: result = Image.new(pil_img.mode, (height, height), background_color) result.paste(pil_img, ((height - width) // 2, 0)) return result def process_images(images, image_processor, model_cfg): image_aspect_ratio = getattr(model_cfg, "image_aspect_ratio", None) new_images = [] if image_aspect_ratio == 'pad': for image in images: image = expand2square(image, tuple(int(x*255) for x in image_processor.image_mean)) image = image_processor.preprocess(image, return_tensors='pt')['pixel_values'][0] new_images.append(image) elif image_aspect_ratio == "anyres": for image in images: image = process_anyres_image(image, image_processor, model_cfg.image_grid_pinpoints) new_images.append(image) else: return image_processor(images, return_tensors='pt')['pixel_values'] if all(x.shape == new_images[0].shape for x in new_images): new_images = torch.stack(new_images, dim=0) return new_images def tokenizer_image_token(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None): prompt_chunks = [tokenizer(chunk).input_ids for chunk in prompt.split('')] def insert_separator(X, sep): return [ele for sublist in zip(X, [sep]*len(X)) for ele in sublist][:-1] input_ids = [] offset = 0 if len(prompt_chunks) > 0 and len(prompt_chunks[0]) > 0 and prompt_chunks[0][0] == tokenizer.bos_token_id: offset = 1 input_ids.append(prompt_chunks[0][0]) for x in insert_separator(prompt_chunks, [image_token_index] * (offset + 1)): input_ids.extend(x[offset:]) if return_tensors is not None: if return_tensors == 'pt': return torch.tensor(input_ids, dtype=torch.long) raise ValueError(f'Unsupported tensor type: {return_tensors}') return input_ids def get_model_name_from_path(model_path): model_path = model_path.strip("/") model_paths = model_path.split("/") if model_paths[-1].startswith('checkpoint-'): return model_paths[-2] + "_" + model_paths[-1] else: return model_paths[-1] class KeywordsStoppingCriteria(StoppingCriteria): def __init__(self, keywords, tokenizer, input_ids): self.keywords = keywords self.keyword_ids = [] self.max_keyword_len = 0 for keyword in keywords: cur_keyword_ids = tokenizer(keyword).input_ids if len(cur_keyword_ids) > 1 and cur_keyword_ids[0] == tokenizer.bos_token_id: cur_keyword_ids = cur_keyword_ids[1:] if len(cur_keyword_ids) > self.max_keyword_len: self.max_keyword_len = len(cur_keyword_ids) self.keyword_ids.append(torch.tensor(cur_keyword_ids)) self.tokenizer = tokenizer self.start_len = input_ids.shape[1] def call_for_batch(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool: offset = min(output_ids.shape[1] - self.start_len, self.max_keyword_len) self.keyword_ids = [keyword_id.to(output_ids.device) for keyword_id in self.keyword_ids] for keyword_id in self.keyword_ids: truncated_output_ids = output_ids[0, -keyword_id.shape[0]:] if torch.equal(truncated_output_ids, keyword_id): return True outputs = self.tokenizer.batch_decode(output_ids[:, -offset:], skip_special_tokens=True)[0] for keyword in self.keywords: if keyword in outputs: return True return False def __call__(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool: outputs = [] for i in range(output_ids.shape[0]): outputs.append(self.call_for_batch(output_ids[i].unsqueeze(0), scores)) return all(outputs) ================================================ FILE: llava/model/__init__.py ================================================ try: from .language_model.llava_llama import LlavaLlamaForCausalLM, LlavaConfig from .language_model.llava_mpt import LlavaMptForCausalLM, LlavaMptConfig from .language_model.llava_mistral import LlavaMistralForCausalLM, LlavaMistralConfig except: pass ================================================ FILE: llava/model/apply_delta.py ================================================ """ Usage: python3 -m fastchat.model.apply_delta --base ~/model_weights/llama-7b --target ~/model_weights/vicuna-7b --delta lmsys/vicuna-7b-delta """ import argparse import torch from tqdm import tqdm from transformers import AutoTokenizer, AutoModelForCausalLM from llava import LlavaLlamaForCausalLM def apply_delta(base_model_path, target_model_path, delta_path): print("Loading base model") base = AutoModelForCausalLM.from_pretrained( base_model_path, torch_dtype=torch.float16, low_cpu_mem_usage=True) print("Loading delta") delta = LlavaLlamaForCausalLM.from_pretrained(delta_path, torch_dtype=torch.float16, low_cpu_mem_usage=True) delta_tokenizer = AutoTokenizer.from_pretrained(delta_path) print("Applying delta") for name, param in tqdm(delta.state_dict().items(), desc="Applying delta"): if name not in base.state_dict(): assert name in ['model.mm_projector.weight', 'model.mm_projector.bias'], f'{name} not in base model' continue if param.data.shape == base.state_dict()[name].shape: param.data += base.state_dict()[name] else: assert name in ['model.embed_tokens.weight', 'lm_head.weight'], \ f'{name} dimension mismatch: {param.data.shape} vs {base.state_dict()[name].shape}' bparam = base.state_dict()[name] param.data[:bparam.shape[0], :bparam.shape[1]] += bparam print("Saving target model") delta.save_pretrained(target_model_path) delta_tokenizer.save_pretrained(target_model_path) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--base-model-path", type=str, required=True) parser.add_argument("--target-model-path", type=str, required=True) parser.add_argument("--delta-path", type=str, required=True) args = parser.parse_args() apply_delta(args.base_model_path, args.target_model_path, args.delta_path) ================================================ FILE: llava/model/builder.py ================================================ # Copyright 2023 Haotian Liu # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. import os import warnings import shutil from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig, BitsAndBytesConfig import torch from llava.model import * from llava.constants import DEFAULT_IMAGE_PATCH_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN def load_pretrained_model(model_path, model_base, model_name, load_8bit=False, load_4bit=False, device_map="auto", device="cuda", use_flash_attn=False, **kwargs): kwargs = {"device_map": device_map, **kwargs} if device != "cuda": kwargs['device_map'] = {"": device} if load_8bit: kwargs['load_in_8bit'] = True elif load_4bit: kwargs['load_in_4bit'] = True kwargs['quantization_config'] = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ) else: kwargs['torch_dtype'] = torch.float16 if use_flash_attn: kwargs['attn_implementation'] = 'flash_attention_2' if 'llava' in model_name.lower(): # Load LLaVA model if 'lora' in model_name.lower() and model_base is None: warnings.warn('There is `lora` in model name but no `model_base` is provided. If you are loading a LoRA model, please provide the `model_base` argument. Detailed instruction: https://github.com/haotian-liu/LLaVA#launch-a-model-worker-lora-weights-unmerged.') if 'lora' in model_name.lower() and model_base is not None: from llava.model.language_model.llava_llama import LlavaConfig lora_cfg_pretrained = LlavaConfig.from_pretrained(model_path) tokenizer = AutoTokenizer.from_pretrained(model_base, use_fast=False) print('Loading LLaVA from base model...') model = LlavaLlamaForCausalLM.from_pretrained(model_base, low_cpu_mem_usage=True, config=lora_cfg_pretrained, **kwargs) token_num, tokem_dim = model.lm_head.out_features, model.lm_head.in_features if model.lm_head.weight.shape[0] != token_num: model.lm_head.weight = torch.nn.Parameter(torch.empty(token_num, tokem_dim, device=model.device, dtype=model.dtype)) model.model.embed_tokens.weight = torch.nn.Parameter(torch.empty(token_num, tokem_dim, device=model.device, dtype=model.dtype)) print('Loading additional LLaVA weights...') if os.path.exists(os.path.join(model_path, 'non_lora_trainables.bin')): non_lora_trainables = torch.load(os.path.join(model_path, 'non_lora_trainables.bin'), map_location='cpu') else: # this is probably from HF Hub from huggingface_hub import hf_hub_download def load_from_hf(repo_id, filename, subfolder=None): cache_file = hf_hub_download( repo_id=repo_id, filename=filename, subfolder=subfolder) return torch.load(cache_file, map_location='cpu') non_lora_trainables = load_from_hf(model_path, 'non_lora_trainables.bin') non_lora_trainables = {(k[11:] if k.startswith('base_model.') else k): v for k, v in non_lora_trainables.items()} if any(k.startswith('model.model.') for k in non_lora_trainables): non_lora_trainables = {(k[6:] if k.startswith('model.') else k): v for k, v in non_lora_trainables.items()} model.load_state_dict(non_lora_trainables, strict=False) from peft import PeftModel print('Loading LoRA weights...') model = PeftModel.from_pretrained(model, model_path) print('Merging LoRA weights...') model = model.merge_and_unload() print('Model is loaded...') elif model_base is not None: # this may be mm projector only print('Loading LLaVA from base model...') if 'mpt' in model_name.lower(): if not os.path.isfile(os.path.join(model_path, 'configuration_mpt.py')): shutil.copyfile(os.path.join(model_base, 'configuration_mpt.py'), os.path.join(model_path, 'configuration_mpt.py')) tokenizer = AutoTokenizer.from_pretrained(model_base, use_fast=True) cfg_pretrained = AutoConfig.from_pretrained(model_path, trust_remote_code=True) model = LlavaMptForCausalLM.from_pretrained(model_base, low_cpu_mem_usage=True, config=cfg_pretrained, **kwargs) else: tokenizer = AutoTokenizer.from_pretrained(model_base, use_fast=False) cfg_pretrained = AutoConfig.from_pretrained(model_path) model = LlavaLlamaForCausalLM.from_pretrained(model_base, low_cpu_mem_usage=True, config=cfg_pretrained, **kwargs) mm_projector_weights = torch.load(os.path.join(model_path, 'mm_projector.bin'), map_location='cpu') mm_projector_weights = {k: v.to(torch.float16) for k, v in mm_projector_weights.items()} model.load_state_dict(mm_projector_weights, strict=False) else: if 'mpt' in model_name.lower(): tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True) model = LlavaMptForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, **kwargs) elif 'mistral' in model_name.lower(): tokenizer = AutoTokenizer.from_pretrained(model_path) model = LlavaMistralForCausalLM.from_pretrained( model_path, low_cpu_mem_usage=True, **kwargs ) else: tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) model = LlavaLlamaForCausalLM.from_pretrained( model_path, low_cpu_mem_usage=True, **kwargs ) else: # Load language model if model_base is not None: # PEFT model from peft import PeftModel tokenizer = AutoTokenizer.from_pretrained(model_base, use_fast=False) model = AutoModelForCausalLM.from_pretrained(model_base, low_cpu_mem_usage=True, **kwargs) print(f"Loading LoRA weights from {model_path}") model = PeftModel.from_pretrained(model, model_path) print(f"Merging weights") model = model.merge_and_unload() print('Convert to FP16...') model.to(torch.float16) else: use_fast = False if 'mpt' in model_name.lower(): tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True) model = AutoModelForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, trust_remote_code=True, **kwargs) else: tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) model = AutoModelForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, **kwargs) image_processor = None if 'llava' in model_name.lower(): mm_use_im_start_end = getattr(model.config, "mm_use_im_start_end", False) mm_use_im_patch_token = getattr(model.config, "mm_use_im_patch_token", True) if mm_use_im_patch_token: tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True) if mm_use_im_start_end: tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True) model.resize_token_embeddings(len(tokenizer)) vision_tower = model.get_vision_tower() if not vision_tower.is_loaded: vision_tower.load_model(device_map=device_map) if device_map != 'auto': vision_tower.to(device=device_map, dtype=torch.float16) image_processor = vision_tower.image_processor if hasattr(model.config, "max_sequence_length"): context_len = model.config.max_sequence_length else: context_len = 2048 return tokenizer, model, image_processor, context_len ================================================ FILE: llava/model/consolidate.py ================================================ """ Usage: python3 -m llava.model.consolidate --src ~/model_weights/llava-7b --dst ~/model_weights/llava-7b_consolidate """ import argparse import torch from transformers import AutoTokenizer, AutoModelForCausalLM from llava.model import * from llava.model.utils import auto_upgrade def consolidate_ckpt(src_path, dst_path): print("Loading model") auto_upgrade(src_path) src_model = AutoModelForCausalLM.from_pretrained(src_path, torch_dtype=torch.float16, low_cpu_mem_usage=True) src_tokenizer = AutoTokenizer.from_pretrained(src_path, use_fast=False) src_model.save_pretrained(dst_path) src_tokenizer.save_pretrained(dst_path) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--src", type=str, required=True) parser.add_argument("--dst", type=str, required=True) args = parser.parse_args() consolidate_ckpt(args.src, args.dst) ================================================ FILE: llava/model/language_model/llava_llama.py ================================================ # Copyright 2023 Haotian Liu # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from typing import List, Optional, Tuple, Union import torch import torch.nn as nn from transformers import AutoConfig, AutoModelForCausalLM, \ LlamaConfig, LlamaModel, LlamaForCausalLM from transformers.modeling_outputs import CausalLMOutputWithPast from transformers.generation.utils import GenerateOutput from ..llava_arch import LlavaMetaModel, LlavaMetaForCausalLM class LlavaConfig(LlamaConfig): model_type = "llava_llama" class LlavaLlamaModel(LlavaMetaModel, LlamaModel): config_class = LlavaConfig def __init__(self, config: LlamaConfig): super(LlavaLlamaModel, self).__init__(config) class LlavaLlamaForCausalLM(LlamaForCausalLM, LlavaMetaForCausalLM): config_class = LlavaConfig def __init__(self, config): super(LlamaForCausalLM, self).__init__(config) self.model = LlavaLlamaModel(config) self.pretraining_tp = config.pretraining_tp self.vocab_size = config.vocab_size self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False) # Initialize weights and apply final processing self.post_init() def get_model(self): return self.model def forward( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[List[torch.FloatTensor]] = None, inputs_embeds: Optional[torch.FloatTensor] = None, labels: Optional[torch.LongTensor] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, images: Optional[torch.FloatTensor] = None, image_sizes: Optional[List[List[int]]] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple, CausalLMOutputWithPast]: if inputs_embeds is None: ( input_ids, position_ids, attention_mask, past_key_values, inputs_embeds, labels ) = self.prepare_inputs_labels_for_multimodal( input_ids, position_ids, attention_mask, past_key_values, labels, images, image_sizes ) return super().forward( input_ids=input_ids, attention_mask=attention_mask, position_ids=position_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, labels=labels, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict ) @torch.no_grad() def generate( self, inputs: Optional[torch.Tensor] = None, images: Optional[torch.Tensor] = None, image_sizes: Optional[torch.Tensor] = None, **kwargs, ) -> Union[GenerateOutput, torch.LongTensor]: position_ids = kwargs.pop("position_ids", None) attention_mask = kwargs.pop("attention_mask", None) if "inputs_embeds" in kwargs: raise NotImplementedError("`inputs_embeds` is not supported") if images is not None: ( inputs, position_ids, attention_mask, _, inputs_embeds, _ ) = self.prepare_inputs_labels_for_multimodal( inputs, position_ids, attention_mask, None, None, images, image_sizes=image_sizes ) else: inputs_embeds = self.get_model().embed_tokens(inputs) return super().generate( position_ids=position_ids, attention_mask=attention_mask, inputs_embeds=inputs_embeds, **kwargs ) def prepare_inputs_for_generation(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs): images = kwargs.pop("images", None) image_sizes = kwargs.pop("image_sizes", None) inputs = super().prepare_inputs_for_generation( input_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, **kwargs ) if images is not None: inputs['images'] = images if image_sizes is not None: inputs['image_sizes'] = image_sizes return inputs AutoConfig.register("llava_llama", LlavaConfig) AutoModelForCausalLM.register(LlavaConfig, LlavaLlamaForCausalLM) ================================================ FILE: llava/model/language_model/llava_mistral.py ================================================ # Copyright 2023 Haotian Liu # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from typing import List, Optional, Tuple, Union import torch import torch.nn as nn from torch.nn import CrossEntropyLoss from transformers import AutoConfig, AutoModelForCausalLM, \ MistralConfig, MistralModel, MistralForCausalLM from transformers.modeling_outputs import CausalLMOutputWithPast from transformers.generation.utils import GenerateOutput from ..llava_arch import LlavaMetaModel, LlavaMetaForCausalLM class LlavaMistralConfig(MistralConfig): model_type = "llava_mistral" class LlavaMistralModel(LlavaMetaModel, MistralModel): config_class = LlavaMistralConfig def __init__(self, config: MistralConfig): super(LlavaMistralModel, self).__init__(config) class LlavaMistralForCausalLM(MistralForCausalLM, LlavaMetaForCausalLM): config_class = LlavaMistralConfig def __init__(self, config): super(MistralForCausalLM, self).__init__(config) self.model = LlavaMistralModel(config) self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False) # Initialize weights and apply final processing self.post_init() def get_model(self): return self.model def forward( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[List[torch.FloatTensor]] = None, inputs_embeds: Optional[torch.FloatTensor] = None, labels: Optional[torch.LongTensor] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, images: Optional[torch.FloatTensor] = None, image_sizes: Optional[List[List[int]]] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple, CausalLMOutputWithPast]: if inputs_embeds is None: ( input_ids, position_ids, attention_mask, past_key_values, inputs_embeds, labels ) = self.prepare_inputs_labels_for_multimodal( input_ids, position_ids, attention_mask, past_key_values, labels, images, image_sizes ) return super().forward( input_ids=input_ids, attention_mask=attention_mask, position_ids=position_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, labels=labels, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict ) @torch.no_grad() def generate( self, inputs: Optional[torch.Tensor] = None, images: Optional[torch.Tensor] = None, image_sizes: Optional[torch.Tensor] = None, **kwargs, ) -> Union[GenerateOutput, torch.LongTensor]: position_ids = kwargs.pop("position_ids", None) attention_mask = kwargs.pop("attention_mask", None) if "inputs_embeds" in kwargs: raise NotImplementedError("`inputs_embeds` is not supported") if images is not None: ( inputs, position_ids, attention_mask, _, inputs_embeds, _ ) = self.prepare_inputs_labels_for_multimodal( inputs, position_ids, attention_mask, None, None, images, image_sizes=image_sizes ) else: inputs_embeds = self.get_model().embed_tokens(inputs) return super().generate( position_ids=position_ids, attention_mask=attention_mask, inputs_embeds=inputs_embeds, **kwargs ) def prepare_inputs_for_generation(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs): images = kwargs.pop("images", None) image_sizes = kwargs.pop("image_sizes", None) inputs = super().prepare_inputs_for_generation( input_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, **kwargs ) if images is not None: inputs['images'] = images if image_sizes is not None: inputs['image_sizes'] = image_sizes return inputs AutoConfig.register("llava_mistral", LlavaMistralConfig) AutoModelForCausalLM.register(LlavaMistralConfig, LlavaMistralForCausalLM) ================================================ FILE: llava/model/language_model/llava_mpt.py ================================================ # Copyright 2023 Haotian Liu # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from typing import Optional, Tuple import torch from transformers import AutoConfig, AutoModelForCausalLM, \ MptConfig, MptForCausalLM, MptModel from llava.model.llava_arch import LlavaMetaModel, LlavaMetaForCausalLM class LlavaMptConfig(MptConfig): model_type = "llava_mpt" class LlavaMptModel(LlavaMetaModel, MptModel): config_class = LlavaMptConfig def __init__(self, config: MptConfig): config.hidden_size = config.d_model super(LlavaMptModel, self).__init__(config) def embed_tokens(self, x): return self.wte(x) class LlavaMptForCausalLM(MptForCausalLM, LlavaMetaForCausalLM): config_class = LlavaMptConfig supports_gradient_checkpointing = True def __init__(self, config): super(MptForCausalLM, self).__init__(config) self.transformer = LlavaMptModel(config) self.lm_head = torch.nn.Linear(config.hidden_size, config.vocab_size, bias=False) # Initialize weights and apply final processing self.post_init() def get_model(self): return self.transformer def _set_gradient_checkpointing(self, module, value=False): if isinstance(module, LlavaMptModel): module.gradient_checkpointing = value def forward( self, input_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None, attention_mask: Optional[torch.Tensor] = None, inputs_embeds: Optional[torch.Tensor] = None, labels: Optional[torch.Tensor] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, images=None): input_ids, attention_mask, past_key_values, inputs_embeds, labels = self.prepare_inputs_labels_for_multimodal(input_ids, attention_mask, past_key_values, labels, images) return super().forward( input_ids, past_key_values=past_key_values, attention_mask=attention_mask, inputs_embeds=inputs_embeds, labels=labels, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict, ) def prepare_inputs_for_generation(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs): images = kwargs.pop("images", None) _inputs = super().prepare_inputs_for_generation( input_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, **kwargs ) _inputs['images'] = images return _inputs AutoConfig.register("llava_mpt", LlavaMptConfig) AutoModelForCausalLM.register(LlavaMptConfig, LlavaMptForCausalLM) ================================================ FILE: llava/model/llava_arch.py ================================================ # Copyright 2023 Haotian Liu # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. from abc import ABC, abstractmethod import torch import torch.nn as nn from .multimodal_encoder.builder import build_vision_tower from .multimodal_projector.builder import build_vision_projector from llava.constants import IGNORE_INDEX, IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_PATCH_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from llava.mm_utils import get_anyres_image_grid_shape class LlavaMetaModel: def __init__(self, config): super(LlavaMetaModel, self).__init__(config) if hasattr(config, "mm_vision_tower"): self.vision_tower = build_vision_tower(config, delay_load=True) self.mm_projector = build_vision_projector(config) if 'unpad' in getattr(config, 'mm_patch_merge_type', ''): self.image_newline = nn.Parameter( torch.empty(config.hidden_size, dtype=self.dtype) ) def get_vision_tower(self): vision_tower = getattr(self, 'vision_tower', None) if type(vision_tower) is list: vision_tower = vision_tower[0] return vision_tower def initialize_vision_modules(self, model_args, fsdp=None): vision_tower = model_args.vision_tower mm_vision_select_layer = model_args.mm_vision_select_layer mm_vision_select_feature = model_args.mm_vision_select_feature pretrain_mm_mlp_adapter = model_args.pretrain_mm_mlp_adapter mm_patch_merge_type = model_args.mm_patch_merge_type self.config.mm_vision_tower = vision_tower if self.get_vision_tower() is None: vision_tower = build_vision_tower(model_args) if fsdp is not None and len(fsdp) > 0: self.vision_tower = [vision_tower] else: self.vision_tower = vision_tower else: if fsdp is not None and len(fsdp) > 0: vision_tower = self.vision_tower[0] else: vision_tower = self.vision_tower vision_tower.load_model() self.config.use_mm_proj = True self.config.mm_projector_type = getattr(model_args, 'mm_projector_type', 'linear') self.config.mm_hidden_size = vision_tower.hidden_size self.config.mm_vision_select_layer = mm_vision_select_layer self.config.mm_vision_select_feature = mm_vision_select_feature self.config.mm_patch_merge_type = mm_patch_merge_type if getattr(self, 'mm_projector', None) is None: self.mm_projector = build_vision_projector(self.config) if 'unpad' in mm_patch_merge_type: embed_std = 1 / torch.sqrt(torch.tensor(self.config.hidden_size, dtype=self.dtype)) self.image_newline = nn.Parameter( torch.randn(self.config.hidden_size, dtype=self.dtype) * embed_std ) else: # In case it is frozen by LoRA for p in self.mm_projector.parameters(): p.requires_grad = True if pretrain_mm_mlp_adapter is not None: mm_projector_weights = torch.load(pretrain_mm_mlp_adapter, map_location='cpu') def get_w(weights, keyword): return {k.split(keyword + '.')[1]: v for k, v in weights.items() if keyword in k} self.mm_projector.load_state_dict(get_w(mm_projector_weights, 'mm_projector')) def unpad_image(tensor, original_size): """ Unpads a PyTorch tensor of a padded and resized image. Args: tensor (torch.Tensor): The image tensor, assumed to be in CxHxW format. original_size (tuple): The original size of PIL image (width, height). Returns: torch.Tensor: The unpadded image tensor. """ original_width, original_height = original_size current_height, current_width = tensor.shape[1:] original_aspect_ratio = original_width / original_height current_aspect_ratio = current_width / current_height if original_aspect_ratio > current_aspect_ratio: scale_factor = current_width / original_width new_height = int(original_height * scale_factor) padding = (current_height - new_height) // 2 unpadded_tensor = tensor[:, padding:current_height - padding, :] else: scale_factor = current_height / original_height new_width = int(original_width * scale_factor) padding = (current_width - new_width) // 2 unpadded_tensor = tensor[:, :, padding:current_width - padding] return unpadded_tensor class LlavaMetaForCausalLM(ABC): @abstractmethod def get_model(self): pass def get_vision_tower(self): return self.get_model().get_vision_tower() def encode_images(self, images): image_features = self.get_model().get_vision_tower()(images) image_features = self.get_model().mm_projector(image_features) return image_features def prepare_inputs_labels_for_multimodal( self, input_ids, position_ids, attention_mask, past_key_values, labels, images, image_sizes=None ): vision_tower = self.get_vision_tower() if vision_tower is None or images is None or input_ids.shape[1] == 1: return input_ids, position_ids, attention_mask, past_key_values, None, labels if type(images) is list or images.ndim == 5: if type(images) is list: images = [x.unsqueeze(0) if x.ndim == 3 else x for x in images] concat_images = torch.cat([image for image in images], dim=0) image_features = self.encode_images(concat_images) split_sizes = [image.shape[0] for image in images] image_features = torch.split(image_features, split_sizes, dim=0) mm_patch_merge_type = getattr(self.config, 'mm_patch_merge_type', 'flat') image_aspect_ratio = getattr(self.config, 'image_aspect_ratio', 'square') if mm_patch_merge_type == 'flat': image_features = [x.flatten(0, 1) for x in image_features] elif mm_patch_merge_type.startswith('spatial'): new_image_features = [] for image_idx, image_feature in enumerate(image_features): if image_feature.shape[0] > 1: base_image_feature = image_feature[0] image_feature = image_feature[1:] height = width = self.get_vision_tower().num_patches_per_side assert height * width == base_image_feature.shape[0] if image_aspect_ratio == 'anyres': num_patch_width, num_patch_height = get_anyres_image_grid_shape(image_sizes[image_idx], self.config.image_grid_pinpoints, self.get_vision_tower().config.image_size) image_feature = image_feature.view(num_patch_height, num_patch_width, height, width, -1) else: raise NotImplementedError if 'unpad' in mm_patch_merge_type: image_feature = image_feature.permute(4, 0, 2, 1, 3).contiguous() image_feature = image_feature.flatten(1, 2).flatten(2, 3) image_feature = unpad_image(image_feature, image_sizes[image_idx]) image_feature = torch.cat(( image_feature, self.model.image_newline[:, None, None].expand(*image_feature.shape[:-1], 1).to(image_feature.device) ), dim=-1) image_feature = image_feature.flatten(1, 2).transpose(0, 1) else: image_feature = image_feature.permute(0, 2, 1, 3, 4).contiguous() image_feature = image_feature.flatten(0, 3) image_feature = torch.cat((base_image_feature, image_feature), dim=0) else: image_feature = image_feature[0] if 'unpad' in mm_patch_merge_type: image_feature = torch.cat(( image_feature, self.model.image_newline[None].to(image_feature.device) ), dim=0) new_image_features.append(image_feature) image_features = new_image_features else: raise ValueError(f"Unexpected mm_patch_merge_type: {self.config.mm_patch_merge_type}") else: image_features = self.encode_images(images) # TODO: image start / end is not implemented here to support pretraining. if getattr(self.config, 'tune_mm_mlp_adapter', False) and getattr(self.config, 'mm_use_im_start_end', False): raise NotImplementedError # Let's just add dummy tensors if they do not exist, # it is a headache to deal with None all the time. # But it is not ideal, and if you have a better idea, # please open an issue / submit a PR, thanks. _labels = labels _position_ids = position_ids _attention_mask = attention_mask if attention_mask is None: attention_mask = torch.ones_like(input_ids, dtype=torch.bool) else: attention_mask = attention_mask.bool() if position_ids is None: position_ids = torch.arange(0, input_ids.shape[1], dtype=torch.long, device=input_ids.device) if labels is None: labels = torch.full_like(input_ids, IGNORE_INDEX) # remove the padding using attention_mask -- FIXME _input_ids = input_ids input_ids = [cur_input_ids[cur_attention_mask] for cur_input_ids, cur_attention_mask in zip(input_ids, attention_mask)] labels = [cur_labels[cur_attention_mask] for cur_labels, cur_attention_mask in zip(labels, attention_mask)] new_input_embeds = [] new_labels = [] cur_image_idx = 0 for batch_idx, cur_input_ids in enumerate(input_ids): num_images = (cur_input_ids == IMAGE_TOKEN_INDEX).sum() if num_images == 0: cur_image_features = image_features[cur_image_idx] cur_input_embeds_1 = self.get_model().embed_tokens(cur_input_ids) cur_input_embeds = torch.cat([cur_input_embeds_1, cur_image_features[0:0]], dim=0) new_input_embeds.append(cur_input_embeds) new_labels.append(labels[batch_idx]) cur_image_idx += 1 continue image_token_indices = [-1] + torch.where(cur_input_ids == IMAGE_TOKEN_INDEX)[0].tolist() + [cur_input_ids.shape[0]] cur_input_ids_noim = [] cur_labels = labels[batch_idx] cur_labels_noim = [] for i in range(len(image_token_indices) - 1): cur_input_ids_noim.append(cur_input_ids[image_token_indices[i]+1:image_token_indices[i+1]]) cur_labels_noim.append(cur_labels[image_token_indices[i]+1:image_token_indices[i+1]]) split_sizes = [x.shape[0] for x in cur_labels_noim] cur_input_embeds = self.get_model().embed_tokens(torch.cat(cur_input_ids_noim)) cur_input_embeds_no_im = torch.split(cur_input_embeds, split_sizes, dim=0) cur_new_input_embeds = [] cur_new_labels = [] for i in range(num_images + 1): cur_new_input_embeds.append(cur_input_embeds_no_im[i]) cur_new_labels.append(cur_labels_noim[i]) if i < num_images: cur_image_features = image_features[cur_image_idx] cur_image_idx += 1 cur_new_input_embeds.append(cur_image_features) cur_new_labels.append(torch.full((cur_image_features.shape[0],), IGNORE_INDEX, device=cur_labels.device, dtype=cur_labels.dtype)) cur_new_input_embeds = [x.to(self.device) for x in cur_new_input_embeds] cur_new_input_embeds = torch.cat(cur_new_input_embeds) cur_new_labels = torch.cat(cur_new_labels) new_input_embeds.append(cur_new_input_embeds) new_labels.append(cur_new_labels) # Truncate sequences to max length as image embeddings can make the sequence longer tokenizer_model_max_length = getattr(self.config, 'tokenizer_model_max_length', None) if tokenizer_model_max_length is not None: new_input_embeds = [x[:tokenizer_model_max_length] for x in new_input_embeds] new_labels = [x[:tokenizer_model_max_length] for x in new_labels] # Combine them max_len = max(x.shape[0] for x in new_input_embeds) batch_size = len(new_input_embeds) new_input_embeds_padded = [] new_labels_padded = torch.full((batch_size, max_len), IGNORE_INDEX, dtype=new_labels[0].dtype, device=new_labels[0].device) attention_mask = torch.zeros((batch_size, max_len), dtype=attention_mask.dtype, device=attention_mask.device) position_ids = torch.zeros((batch_size, max_len), dtype=position_ids.dtype, device=position_ids.device) for i, (cur_new_embed, cur_new_labels) in enumerate(zip(new_input_embeds, new_labels)): cur_len = cur_new_embed.shape[0] if getattr(self.config, 'tokenizer_padding_side', 'right') == "left": new_input_embeds_padded.append(torch.cat(( torch.zeros((max_len - cur_len, cur_new_embed.shape[1]), dtype=cur_new_embed.dtype, device=cur_new_embed.device), cur_new_embed ), dim=0)) if cur_len > 0: new_labels_padded[i, -cur_len:] = cur_new_labels attention_mask[i, -cur_len:] = True position_ids[i, -cur_len:] = torch.arange(0, cur_len, dtype=position_ids.dtype, device=position_ids.device) else: new_input_embeds_padded.append(torch.cat(( cur_new_embed, torch.zeros((max_len - cur_len, cur_new_embed.shape[1]), dtype=cur_new_embed.dtype, device=cur_new_embed.device) ), dim=0)) if cur_len > 0: new_labels_padded[i, :cur_len] = cur_new_labels attention_mask[i, :cur_len] = True position_ids[i, :cur_len] = torch.arange(0, cur_len, dtype=position_ids.dtype, device=position_ids.device) new_input_embeds = torch.stack(new_input_embeds_padded, dim=0) if _labels is None: new_labels = None else: new_labels = new_labels_padded if _attention_mask is None: attention_mask = None else: attention_mask = attention_mask.to(dtype=_attention_mask.dtype) if _position_ids is None: position_ids = None return None, position_ids, attention_mask, past_key_values, new_input_embeds, new_labels def initialize_vision_tokenizer(self, model_args, tokenizer): if model_args.mm_use_im_patch_token: tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True) self.resize_token_embeddings(len(tokenizer)) if model_args.mm_use_im_start_end: num_new_tokens = tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True) self.resize_token_embeddings(len(tokenizer)) if num_new_tokens > 0: input_embeddings = self.get_input_embeddings().weight.data output_embeddings = self.get_output_embeddings().weight.data input_embeddings_avg = input_embeddings[:-num_new_tokens].mean( dim=0, keepdim=True) output_embeddings_avg = output_embeddings[:-num_new_tokens].mean( dim=0, keepdim=True) input_embeddings[-num_new_tokens:] = input_embeddings_avg output_embeddings[-num_new_tokens:] = output_embeddings_avg if model_args.tune_mm_mlp_adapter: for p in self.get_input_embeddings().parameters(): p.requires_grad = True for p in self.get_output_embeddings().parameters(): p.requires_grad = False if model_args.pretrain_mm_mlp_adapter: mm_projector_weights = torch.load(model_args.pretrain_mm_mlp_adapter, map_location='cpu') embed_tokens_weight = mm_projector_weights['model.embed_tokens.weight'] assert num_new_tokens == 2 if input_embeddings.shape == embed_tokens_weight.shape: input_embeddings[-num_new_tokens:] = embed_tokens_weight[-num_new_tokens:] elif embed_tokens_weight.shape[0] == num_new_tokens: input_embeddings[-num_new_tokens:] = embed_tokens_weight else: raise ValueError(f"Unexpected embed_tokens_weight shape. Pretrained: {embed_tokens_weight.shape}. Current: {input_embeddings.shape}. Numer of new tokens: {num_new_tokens}.") elif model_args.mm_use_im_patch_token: if model_args.tune_mm_mlp_adapter: for p in self.get_input_embeddings().parameters(): p.requires_grad = False for p in self.get_output_embeddings().parameters(): p.requires_grad = False ================================================ FILE: llava/model/make_delta.py ================================================ """ Usage: python3 -m llava.model.make_delta --base ~/model_weights/llama-7b --target ~/model_weights/llava-7b --delta ~/model_weights/llava-7b-delta --hub-repo-id liuhaotian/llava-7b-delta """ import argparse import torch from tqdm import tqdm from transformers import AutoTokenizer, AutoModelForCausalLM from llava.model.utils import auto_upgrade def make_delta(base_model_path, target_model_path, delta_path, hub_repo_id): print("Loading base model") base = AutoModelForCausalLM.from_pretrained( base_model_path, torch_dtype=torch.float16, low_cpu_mem_usage=True) print("Loading target model") auto_upgrade(target_model_path) target = AutoModelForCausalLM.from_pretrained(target_model_path, torch_dtype=torch.float16, low_cpu_mem_usage=True) print("Calculating delta") for name, param in tqdm(target.state_dict().items(), desc="Calculating delta"): if name not in base.state_dict(): assert name in ['model.mm_projector.weight', 'model.mm_projector.bias'], f'{name} not in base model' continue if param.data.shape == base.state_dict()[name].shape: param.data -= base.state_dict()[name] else: assert name in ['model.embed_tokens.weight', 'lm_head.weight'], f'{name} dimension mismatch: {param.data.shape} vs {base.state_dict()[name].shape}' bparam = base.state_dict()[name] param.data[:bparam.shape[0], :bparam.shape[1]] -= bparam print("Saving delta") if hub_repo_id: kwargs = {"push_to_hub": True, "repo_id": hub_repo_id} else: kwargs = {} target.save_pretrained(delta_path, **kwargs) target_tokenizer = AutoTokenizer.from_pretrained(target_model_path) target_tokenizer.save_pretrained(delta_path, **kwargs) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--base-model-path", type=str, required=True) parser.add_argument("--target-model-path", type=str, required=True) parser.add_argument("--delta-path", type=str, required=True) parser.add_argument("--hub-repo-id", type=str, default=None) args = parser.parse_args() make_delta(args.base_model_path, args.target_model_path, args.delta_path, args.hub_repo_id) ================================================ FILE: llava/model/multimodal_encoder/builder.py ================================================ import os from .clip_encoder import CLIPVisionTower, CLIPVisionTowerS2 def build_vision_tower(vision_tower_cfg, **kwargs): vision_tower = getattr(vision_tower_cfg, 'mm_vision_tower', getattr(vision_tower_cfg, 'vision_tower', None)) is_absolute_path_exists = os.path.exists(vision_tower) use_s2 = getattr(vision_tower_cfg, 's2', False) if is_absolute_path_exists or vision_tower.startswith("openai") or vision_tower.startswith("laion") or "ShareGPT4V" in vision_tower: if use_s2: return CLIPVisionTowerS2(vision_tower, args=vision_tower_cfg, **kwargs) else: return CLIPVisionTower(vision_tower, args=vision_tower_cfg, **kwargs) raise ValueError(f'Unknown vision tower: {vision_tower}') ================================================ FILE: llava/model/multimodal_encoder/clip_encoder.py ================================================ import torch import torch.nn as nn from transformers import CLIPVisionModel, CLIPImageProcessor, CLIPVisionConfig class CLIPVisionTower(nn.Module): def __init__(self, vision_tower, args, delay_load=False): super().__init__() self.is_loaded = False self.vision_tower_name = vision_tower self.select_layer = args.mm_vision_select_layer self.select_feature = getattr(args, 'mm_vision_select_feature', 'patch') if not delay_load: self.load_model() elif getattr(args, 'unfreeze_mm_vision_tower', False): self.load_model() else: self.cfg_only = CLIPVisionConfig.from_pretrained(self.vision_tower_name) def load_model(self, device_map=None): if self.is_loaded: print('{} is already loaded, `load_model` called again, skipping.'.format(self.vision_tower_name)) return self.image_processor = CLIPImageProcessor.from_pretrained(self.vision_tower_name) self.vision_tower = CLIPVisionModel.from_pretrained(self.vision_tower_name, device_map=device_map) self.vision_tower.requires_grad_(False) self.is_loaded = True def feature_select(self, image_forward_outs): image_features = image_forward_outs.hidden_states[self.select_layer] if self.select_feature == 'patch': image_features = image_features[:, 1:] elif self.select_feature == 'cls_patch': image_features = image_features else: raise ValueError(f'Unexpected select feature: {self.select_feature}') return image_features @torch.no_grad() def forward(self, images): if type(images) is list: image_features = [] for image in images: image_forward_out = self.vision_tower(image.to(device=self.device, dtype=self.dtype).unsqueeze(0), output_hidden_states=True) image_feature = self.feature_select(image_forward_out).to(image.dtype) image_features.append(image_feature) else: image_forward_outs = self.vision_tower(images.to(device=self.device, dtype=self.dtype), output_hidden_states=True) image_features = self.feature_select(image_forward_outs).to(images.dtype) return image_features @property def dummy_feature(self): return torch.zeros(1, self.hidden_size, device=self.device, dtype=self.dtype) @property def dtype(self): return self.vision_tower.dtype @property def device(self): return self.vision_tower.device @property def config(self): if self.is_loaded: return self.vision_tower.config else: return self.cfg_only @property def hidden_size(self): return self.config.hidden_size @property def num_patches_per_side(self): return self.config.image_size // self.config.patch_size @property def num_patches(self): return (self.config.image_size // self.config.patch_size) ** 2 class CLIPVisionTowerS2(CLIPVisionTower): def __init__(self, vision_tower, args, delay_load=False): super().__init__(vision_tower, args, delay_load) self.s2_scales = getattr(args, 's2_scales', '336,672,1008') self.s2_scales = list(map(int, self.s2_scales.split(','))) self.s2_scales.sort() self.s2_split_size = self.s2_scales[0] self.s2_image_size = self.s2_scales[-1] try: from s2wrapper import forward as multiscale_forward except ImportError: raise ImportError('Package s2wrapper not found! Please install by running: \npip install git+https://github.com/bfshi/scaling_on_scales.git') self.multiscale_forward = multiscale_forward # change resize/crop size in preprocessing to the largest image size in s2_scale if not delay_load or getattr(args, 'unfreeze_mm_vision_tower', False): self.image_processor.size['shortest_edge'] = self.s2_image_size self.image_processor.crop_size['height'] = self.image_processor.crop_size['width'] = self.s2_image_size def load_model(self, device_map=None): if self.is_loaded: print('{} is already loaded, `load_model` called again, skipping.'.format(self.vision_tower_name)) return self.image_processor = CLIPImageProcessor.from_pretrained(self.vision_tower_name) self.vision_tower = CLIPVisionModel.from_pretrained(self.vision_tower_name, device_map=device_map) self.vision_tower.requires_grad_(False) self.image_processor.size['shortest_edge'] = self.s2_image_size self.image_processor.crop_size['height'] = self.image_processor.crop_size['width'] = self.s2_image_size self.is_loaded = True @torch.no_grad() def forward_feature(self, images): image_forward_outs = self.vision_tower(images.to(device=self.device, dtype=self.dtype), output_hidden_states=True) image_features = self.feature_select(image_forward_outs).to(images.dtype) return image_features @torch.no_grad() def forward(self, images): if type(images) is list: image_features = [] for image in images: image_feature = self.multiscale_forward(self.forward_feature, image.unsqueeze(0), img_sizes=self.s2_scales, max_split_size=self.s2_split_size) image_features.append(image_feature) else: image_features = self.multiscale_forward(self.forward_feature, images, img_sizes=self.s2_scales, max_split_size=self.s2_split_size) return image_features @property def hidden_size(self): return self.config.hidden_size * len(self.s2_scales) ================================================ FILE: llava/model/multimodal_projector/builder.py ================================================ import torch import torch.nn as nn import re class IdentityMap(nn.Module): def __init__(self): super().__init__() def forward(self, x, *args, **kwargs): return x @property def config(self): return {"mm_projector_type": 'identity'} class SimpleResBlock(nn.Module): def __init__(self, channels): super().__init__() self.pre_norm = nn.LayerNorm(channels) self.proj = nn.Sequential( nn.Linear(channels, channels), nn.GELU(), nn.Linear(channels, channels) ) def forward(self, x): x = self.pre_norm(x) return x + self.proj(x) def build_vision_projector(config, delay_load=False, **kwargs): projector_type = getattr(config, 'mm_projector_type', 'linear') if projector_type == 'linear': return nn.Linear(config.mm_hidden_size, config.hidden_size) mlp_gelu_match = re.match(r'^mlp(\d+)x_gelu$', projector_type) if mlp_gelu_match: mlp_depth = int(mlp_gelu_match.group(1)) modules = [nn.Linear(config.mm_hidden_size, config.hidden_size)] for _ in range(1, mlp_depth): modules.append(nn.GELU()) modules.append(nn.Linear(config.hidden_size, config.hidden_size)) return nn.Sequential(*modules) if projector_type == 'identity': return IdentityMap() raise ValueError(f'Unknown projector type: {projector_type}') ================================================ FILE: llava/model/utils.py ================================================ from transformers import AutoConfig def auto_upgrade(config): cfg = AutoConfig.from_pretrained(config) if 'llava' in config and 'llava' not in cfg.model_type: assert cfg.model_type == 'llama' print("You are using newer LLaVA code base, while the checkpoint of v0 is from older code base.") print("You must upgrade the checkpoint to the new code base (this can be done automatically).") confirm = input("Please confirm that you want to upgrade the checkpoint. [Y/N]") if confirm.lower() in ["y", "yes"]: print("Upgrading checkpoint...") assert len(cfg.architectures) == 1 setattr(cfg.__class__, "model_type", "llava") cfg.architectures[0] = 'LlavaLlamaForCausalLM' cfg.save_pretrained(config) print("Checkpoint upgraded.") else: print("Checkpoint upgrade aborted.") exit(1) ================================================ FILE: llava/serve/__init__.py ================================================ ================================================ FILE: llava/serve/cli.py ================================================ import argparse import torch from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from llava.conversation import conv_templates, SeparatorStyle from llava.model.builder import load_pretrained_model from llava.utils import disable_torch_init from llava.mm_utils import process_images, tokenizer_image_token, get_model_name_from_path from PIL import Image import requests from PIL import Image from io import BytesIO from transformers import TextStreamer def load_image(image_file): if image_file.startswith('http://') or image_file.startswith('https://'): response = requests.get(image_file) image = Image.open(BytesIO(response.content)).convert('RGB') else: image = Image.open(image_file).convert('RGB') return image def main(args): # Model disable_torch_init() model_name = get_model_name_from_path(args.model_path) tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, args.load_8bit, args.load_4bit, device=args.device) if "llama-2" in model_name.lower(): conv_mode = "llava_llama_2" elif "mistral" in model_name.lower(): conv_mode = "mistral_instruct" elif "v1.6-34b" in model_name.lower(): conv_mode = "chatml_direct" elif "v1" in model_name.lower(): conv_mode = "llava_v1" elif "mpt" in model_name.lower(): conv_mode = "mpt" else: conv_mode = "llava_v0" if args.conv_mode is not None and conv_mode != args.conv_mode: print('[WARNING] the auto inferred conversation mode is {}, while `--conv-mode` is {}, using {}'.format(conv_mode, args.conv_mode, args.conv_mode)) else: args.conv_mode = conv_mode conv = conv_templates[args.conv_mode].copy() if "mpt" in model_name.lower(): roles = ('user', 'assistant') else: roles = conv.roles image = load_image(args.image_file) image_size = image.size # Similar operation in model_worker.py image_tensor = process_images([image], image_processor, model.config) if type(image_tensor) is list: image_tensor = [image.to(model.device, dtype=torch.float16) for image in image_tensor] else: image_tensor = image_tensor.to(model.device, dtype=torch.float16) while True: try: inp = input(f"{roles[0]}: ") except EOFError: inp = "" if not inp: print("exit...") break print(f"{roles[1]}: ", end="") if image is not None: # first message if model.config.mm_use_im_start_end: inp = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + inp else: inp = DEFAULT_IMAGE_TOKEN + '\n' + inp image = None conv.append_message(conv.roles[0], inp) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(model.device) stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2 keywords = [stop_str] streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) with torch.inference_mode(): output_ids = model.generate( input_ids, images=image_tensor, image_sizes=[image_size], do_sample=True if args.temperature > 0 else False, temperature=args.temperature, max_new_tokens=args.max_new_tokens, streamer=streamer, use_cache=True) outputs = tokenizer.decode(output_ids[0]).strip() conv.messages[-1][-1] = outputs if args.debug: print("\n", {"prompt": prompt, "outputs": outputs}, "\n") if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-path", type=str, default="facebook/opt-350m") parser.add_argument("--model-base", type=str, default=None) parser.add_argument("--image-file", type=str, required=True) parser.add_argument("--device", type=str, default="cuda") parser.add_argument("--conv-mode", type=str, default=None) parser.add_argument("--temperature", type=float, default=0.2) parser.add_argument("--max-new-tokens", type=int, default=512) parser.add_argument("--load-8bit", action="store_true") parser.add_argument("--load-4bit", action="store_true") parser.add_argument("--debug", action="store_true") args = parser.parse_args() main(args) ================================================ FILE: llava/serve/controller.py ================================================ """ A controller manages distributed workers. It sends worker addresses to clients. """ import argparse import asyncio import dataclasses from enum import Enum, auto import json import logging import time from typing import List, Union import threading from fastapi import FastAPI, Request from fastapi.responses import StreamingResponse import numpy as np import requests import uvicorn from llava.constants import CONTROLLER_HEART_BEAT_EXPIRATION from llava.utils import build_logger, server_error_msg logger = build_logger("controller", "controller.log") class DispatchMethod(Enum): LOTTERY = auto() SHORTEST_QUEUE = auto() @classmethod def from_str(cls, name): if name == "lottery": return cls.LOTTERY elif name == "shortest_queue": return cls.SHORTEST_QUEUE else: raise ValueError(f"Invalid dispatch method") @dataclasses.dataclass class WorkerInfo: model_names: List[str] speed: int queue_length: int check_heart_beat: bool last_heart_beat: str def heart_beat_controller(controller): while True: time.sleep(CONTROLLER_HEART_BEAT_EXPIRATION) controller.remove_stable_workers_by_expiration() class Controller: def __init__(self, dispatch_method: str): # Dict[str -> WorkerInfo] self.worker_info = {} self.dispatch_method = DispatchMethod.from_str(dispatch_method) self.heart_beat_thread = threading.Thread( target=heart_beat_controller, args=(self,), daemon=True) self.heart_beat_thread.start() logger.info("Init controller") def register_worker(self, worker_name: str, check_heart_beat: bool, worker_status: dict): if worker_name not in self.worker_info: logger.info(f"Register a new worker: {worker_name}") else: logger.info(f"Register an existing worker: {worker_name}") if not worker_status: worker_status = self.get_worker_status(worker_name) if not worker_status: return False self.worker_info[worker_name] = WorkerInfo( worker_status["model_names"], worker_status["speed"], worker_status["queue_length"], check_heart_beat, time.time()) logger.info(f"Register done: {worker_name}, {worker_status}") return True def get_worker_status(self, worker_name: str): try: r = requests.post(worker_name + "/worker_get_status", timeout=5) except requests.exceptions.RequestException as e: logger.error(f"Get status fails: {worker_name}, {e}") return None if r.status_code != 200: logger.error(f"Get status fails: {worker_name}, {r}") return None return r.json() def remove_worker(self, worker_name: str): del self.worker_info[worker_name] def refresh_all_workers(self): old_info = dict(self.worker_info) self.worker_info = {} for w_name, w_info in old_info.items(): if not self.register_worker(w_name, w_info.check_heart_beat, None): logger.info(f"Remove stale worker: {w_name}") def list_models(self): model_names = set() for w_name, w_info in self.worker_info.items(): model_names.update(w_info.model_names) return list(model_names) def get_worker_address(self, model_name: str): if self.dispatch_method == DispatchMethod.LOTTERY: worker_names = [] worker_speeds = [] for w_name, w_info in self.worker_info.items(): if model_name in w_info.model_names: worker_names.append(w_name) worker_speeds.append(w_info.speed) worker_speeds = np.array(worker_speeds, dtype=np.float32) norm = np.sum(worker_speeds) if norm < 1e-4: return "" worker_speeds = worker_speeds / norm if True: # Directly return address pt = np.random.choice(np.arange(len(worker_names)), p=worker_speeds) worker_name = worker_names[pt] return worker_name # Check status before returning while True: pt = np.random.choice(np.arange(len(worker_names)), p=worker_speeds) worker_name = worker_names[pt] if self.get_worker_status(worker_name): break else: self.remove_worker(worker_name) worker_speeds[pt] = 0 norm = np.sum(worker_speeds) if norm < 1e-4: return "" worker_speeds = worker_speeds / norm continue return worker_name elif self.dispatch_method == DispatchMethod.SHORTEST_QUEUE: worker_names = [] worker_qlen = [] for w_name, w_info in self.worker_info.items(): if model_name in w_info.model_names: worker_names.append(w_name) worker_qlen.append(w_info.queue_length / w_info.speed) if len(worker_names) == 0: return "" min_index = np.argmin(worker_qlen) w_name = worker_names[min_index] self.worker_info[w_name].queue_length += 1 logger.info(f"names: {worker_names}, queue_lens: {worker_qlen}, ret: {w_name}") return w_name else: raise ValueError(f"Invalid dispatch method: {self.dispatch_method}") def receive_heart_beat(self, worker_name: str, queue_length: int): if worker_name not in self.worker_info: logger.info(f"Receive unknown heart beat. {worker_name}") return False self.worker_info[worker_name].queue_length = queue_length self.worker_info[worker_name].last_heart_beat = time.time() logger.info(f"Receive heart beat. {worker_name}") return True def remove_stable_workers_by_expiration(self): expire = time.time() - CONTROLLER_HEART_BEAT_EXPIRATION to_delete = [] for worker_name, w_info in self.worker_info.items(): if w_info.check_heart_beat and w_info.last_heart_beat < expire: to_delete.append(worker_name) for worker_name in to_delete: self.remove_worker(worker_name) def worker_api_generate_stream(self, params): worker_addr = self.get_worker_address(params["model"]) if not worker_addr: logger.info(f"no worker: {params['model']}") ret = { "text": server_error_msg, "error_code": 2, } yield json.dumps(ret).encode() + b"\0" try: response = requests.post(worker_addr + "/worker_generate_stream", json=params, stream=True, timeout=5) for chunk in response.iter_lines(decode_unicode=False, delimiter=b"\0"): if chunk: yield chunk + b"\0" except requests.exceptions.RequestException as e: logger.info(f"worker timeout: {worker_addr}") ret = { "text": server_error_msg, "error_code": 3, } yield json.dumps(ret).encode() + b"\0" # Let the controller act as a worker to achieve hierarchical # management. This can be used to connect isolated sub networks. def worker_api_get_status(self): model_names = set() speed = 0 queue_length = 0 for w_name in self.worker_info: worker_status = self.get_worker_status(w_name) if worker_status is not None: model_names.update(worker_status["model_names"]) speed += worker_status["speed"] queue_length += worker_status["queue_length"] return { "model_names": list(model_names), "speed": speed, "queue_length": queue_length, } app = FastAPI() @app.post("/register_worker") async def register_worker(request: Request): data = await request.json() controller.register_worker( data["worker_name"], data["check_heart_beat"], data.get("worker_status", None)) @app.post("/refresh_all_workers") async def refresh_all_workers(): models = controller.refresh_all_workers() @app.post("/list_models") async def list_models(): models = controller.list_models() return {"models": models} @app.post("/get_worker_address") async def get_worker_address(request: Request): data = await request.json() addr = controller.get_worker_address(data["model"]) return {"address": addr} @app.post("/receive_heart_beat") async def receive_heart_beat(request: Request): data = await request.json() exist = controller.receive_heart_beat( data["worker_name"], data["queue_length"]) return {"exist": exist} @app.post("/worker_generate_stream") async def worker_api_generate_stream(request: Request): params = await request.json() generator = controller.worker_api_generate_stream(params) return StreamingResponse(generator) @app.post("/worker_get_status") async def worker_api_get_status(request: Request): return controller.worker_api_get_status() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--host", type=str, default="localhost") parser.add_argument("--port", type=int, default=21001) parser.add_argument("--dispatch-method", type=str, choices=[ "lottery", "shortest_queue"], default="shortest_queue") args = parser.parse_args() logger.info(f"args: {args}") controller = Controller(args.dispatch_method) uvicorn.run(app, host=args.host, port=args.port, log_level="info") ================================================ FILE: llava/serve/gradio_web_server.py ================================================ import argparse import datetime import json import os import time import gradio as gr import requests from llava.conversation import (default_conversation, conv_templates, SeparatorStyle) from llava.constants import LOGDIR from llava.utils import (build_logger, server_error_msg, violates_moderation, moderation_msg) import hashlib logger = build_logger("gradio_web_server", "gradio_web_server.log") headers = {"User-Agent": "LLaVA Client"} no_change_btn = gr.Button() enable_btn = gr.Button(interactive=True) disable_btn = gr.Button(interactive=False) priority = { "vicuna-13b": "aaaaaaa", "koala-13b": "aaaaaab", } def get_conv_log_filename(): t = datetime.datetime.now() name = os.path.join(LOGDIR, f"{t.year}-{t.month:02d}-{t.day:02d}-conv.json") return name def get_model_list(): ret = requests.post(args.controller_url + "/refresh_all_workers") assert ret.status_code == 200 ret = requests.post(args.controller_url + "/list_models") models = ret.json()["models"] models.sort(key=lambda x: priority.get(x, x)) logger.info(f"Models: {models}") return models get_window_url_params = """ function() { const params = new URLSearchParams(window.location.search); url_params = Object.fromEntries(params); console.log(url_params); return url_params; } """ def load_demo(url_params, request: gr.Request): logger.info(f"load_demo. ip: {request.client.host}. params: {url_params}") dropdown_update = gr.Dropdown(visible=True) if "model" in url_params: model = url_params["model"] if model in models: dropdown_update = gr.Dropdown(value=model, visible=True) state = default_conversation.copy() return state, dropdown_update def load_demo_refresh_model_list(request: gr.Request): logger.info(f"load_demo. ip: {request.client.host}") models = get_model_list() state = default_conversation.copy() dropdown_update = gr.Dropdown( choices=models, value=models[0] if len(models) > 0 else "" ) return state, dropdown_update def vote_last_response(state, vote_type, model_selector, request: gr.Request): with open(get_conv_log_filename(), "a") as fout: data = { "tstamp": round(time.time(), 4), "type": vote_type, "model": model_selector, "state": state.dict(), "ip": request.client.host, } fout.write(json.dumps(data) + "\n") def upvote_last_response(state, model_selector, request: gr.Request): logger.info(f"upvote. ip: {request.client.host}") vote_last_response(state, "upvote", model_selector, request) return ("",) + (disable_btn,) * 3 def downvote_last_response(state, model_selector, request: gr.Request): logger.info(f"downvote. ip: {request.client.host}") vote_last_response(state, "downvote", model_selector, request) return ("",) + (disable_btn,) * 3 def flag_last_response(state, model_selector, request: gr.Request): logger.info(f"flag. ip: {request.client.host}") vote_last_response(state, "flag", model_selector, request) return ("",) + (disable_btn,) * 3 def regenerate(state, image_process_mode, request: gr.Request): logger.info(f"regenerate. ip: {request.client.host}") state.messages[-1][-1] = None prev_human_msg = state.messages[-2] if type(prev_human_msg[1]) in (tuple, list): prev_human_msg[1] = (*prev_human_msg[1][:2], image_process_mode) state.skip_next = False return (state, state.to_gradio_chatbot(), "", None) + (disable_btn,) * 5 def clear_history(request: gr.Request): logger.info(f"clear_history. ip: {request.client.host}") state = default_conversation.copy() return (state, state.to_gradio_chatbot(), "", None) + (disable_btn,) * 5 def add_text(state, text, image, image_process_mode, request: gr.Request): logger.info(f"add_text. ip: {request.client.host}. len: {len(text)}") if len(text) <= 0 and image is None: state.skip_next = True return (state, state.to_gradio_chatbot(), "", None) + (no_change_btn,) * 5 if args.moderate: flagged = violates_moderation(text) if flagged: state.skip_next = True return (state, state.to_gradio_chatbot(), moderation_msg, None) + ( no_change_btn,) * 5 text = text[:1536] # Hard cut-off if image is not None: text = text[:1200] # Hard cut-off for images if '' not in text: # text = '' + text text = text + '\n' text = (text, image, image_process_mode) state = default_conversation.copy() state.append_message(state.roles[0], text) state.append_message(state.roles[1], None) state.skip_next = False return (state, state.to_gradio_chatbot(), "", None) + (disable_btn,) * 5 def http_bot(state, model_selector, temperature, top_p, max_new_tokens, request: gr.Request): logger.info(f"http_bot. ip: {request.client.host}") start_tstamp = time.time() model_name = model_selector if state.skip_next: # This generate call is skipped due to invalid inputs yield (state, state.to_gradio_chatbot()) + (no_change_btn,) * 5 return if len(state.messages) == state.offset + 2: # First round of conversation if "llava" in model_name.lower(): if 'llama-2' in model_name.lower(): template_name = "llava_llama_2" elif "mistral" in model_name.lower() or "mixtral" in model_name.lower(): if 'orca' in model_name.lower(): template_name = "mistral_orca" elif 'hermes' in model_name.lower(): template_name = "chatml_direct" else: template_name = "mistral_instruct" elif 'llava-v1.6-34b' in model_name.lower(): template_name = "chatml_direct" elif "v1" in model_name.lower(): if 'mmtag' in model_name.lower(): template_name = "v1_mmtag" elif 'plain' in model_name.lower() and 'finetune' not in model_name.lower(): template_name = "v1_mmtag" else: template_name = "llava_v1" elif "mpt" in model_name.lower(): template_name = "mpt" else: if 'mmtag' in model_name.lower(): template_name = "v0_mmtag" elif 'plain' in model_name.lower() and 'finetune' not in model_name.lower(): template_name = "v0_mmtag" else: template_name = "llava_v0" elif "mpt" in model_name: template_name = "mpt_text" elif "llama-2" in model_name: template_name = "llama_2" else: template_name = "vicuna_v1" new_state = conv_templates[template_name].copy() new_state.append_message(new_state.roles[0], state.messages[-2][1]) new_state.append_message(new_state.roles[1], None) state = new_state # Query worker address controller_url = args.controller_url ret = requests.post(controller_url + "/get_worker_address", json={"model": model_name}) worker_addr = ret.json()["address"] logger.info(f"model_name: {model_name}, worker_addr: {worker_addr}") # No available worker if worker_addr == "": state.messages[-1][-1] = server_error_msg yield (state, state.to_gradio_chatbot(), disable_btn, disable_btn, disable_btn, enable_btn, enable_btn) return # Construct prompt prompt = state.get_prompt() all_images = state.get_images(return_pil=True) all_image_hash = [hashlib.md5(image.tobytes()).hexdigest() for image in all_images] for image, hash in zip(all_images, all_image_hash): t = datetime.datetime.now() filename = os.path.join(LOGDIR, "serve_images", f"{t.year}-{t.month:02d}-{t.day:02d}", f"{hash}.jpg") if not os.path.isfile(filename): os.makedirs(os.path.dirname(filename), exist_ok=True) image.save(filename) # Make requests pload = { "model": model_name, "prompt": prompt, "temperature": float(temperature), "top_p": float(top_p), "max_new_tokens": min(int(max_new_tokens), 1536), "stop": state.sep if state.sep_style in [SeparatorStyle.SINGLE, SeparatorStyle.MPT] else state.sep2, "images": f'List of {len(state.get_images())} images: {all_image_hash}', } logger.info(f"==== request ====\n{pload}") pload['images'] = state.get_images() state.messages[-1][-1] = "▌" yield (state, state.to_gradio_chatbot()) + (disable_btn,) * 5 try: # Stream output response = requests.post(worker_addr + "/worker_generate_stream", headers=headers, json=pload, stream=True, timeout=10) for chunk in response.iter_lines(decode_unicode=False, delimiter=b"\0"): if chunk: data = json.loads(chunk.decode()) if data["error_code"] == 0: output = data["text"][len(prompt):].strip() state.messages[-1][-1] = output + "▌" yield (state, state.to_gradio_chatbot()) + (disable_btn,) * 5 else: output = data["text"] + f" (error_code: {data['error_code']})" state.messages[-1][-1] = output yield (state, state.to_gradio_chatbot()) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn) return time.sleep(0.03) except requests.exceptions.RequestException as e: state.messages[-1][-1] = server_error_msg yield (state, state.to_gradio_chatbot()) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn) return state.messages[-1][-1] = state.messages[-1][-1][:-1] yield (state, state.to_gradio_chatbot()) + (enable_btn,) * 5 finish_tstamp = time.time() logger.info(f"{output}") with open(get_conv_log_filename(), "a") as fout: data = { "tstamp": round(finish_tstamp, 4), "type": "chat", "model": model_name, "start": round(start_tstamp, 4), "finish": round(finish_tstamp, 4), "state": state.dict(), "images": all_image_hash, "ip": request.client.host, } fout.write(json.dumps(data) + "\n") title_markdown = (""" # 🌋 LLaVA: Large Language and Vision Assistant [[Project Page](https://llava-vl.github.io)] [[Code](https://github.com/haotian-liu/LLaVA)] [[Model](https://github.com/haotian-liu/LLaVA/blob/main/docs/MODEL_ZOO.md)] | 📚 [[LLaVA](https://arxiv.org/abs/2304.08485)] [[LLaVA-v1.5](https://arxiv.org/abs/2310.03744)] [[LLaVA-v1.6](https://llava-vl.github.io/blog/2024-01-30-llava-1-6/)] """) tos_markdown = (""" ### Terms of use By using this service, users are required to agree to the following terms: The service is a research preview intended for non-commercial use only. It only provides limited safety measures and may generate offensive content. It must not be used for any illegal, harmful, violent, racist, or sexual purposes. The service may collect user dialogue data for future research. Please click the "Flag" button if you get any inappropriate answer! We will collect those to keep improving our moderator. For an optimal experience, please use desktop computers for this demo, as mobile devices may compromise its quality. """) learn_more_markdown = (""" ### License The service is a research preview intended for non-commercial use only, subject to the model [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation. """) block_css = """ #buttons button { min-width: min(120px,100%); } """ def build_demo(embed_mode, cur_dir=None, concurrency_count=10): textbox = gr.Textbox(show_label=False, placeholder="Enter text and press ENTER", container=False) with gr.Blocks(title="LLaVA", theme=gr.themes.Default(), css=block_css) as demo: state = gr.State() if not embed_mode: gr.Markdown(title_markdown) with gr.Row(): with gr.Column(scale=3): with gr.Row(elem_id="model_selector_row"): model_selector = gr.Dropdown( choices=models, value=models[0] if len(models) > 0 else "", interactive=True, show_label=False, container=False) imagebox = gr.Image(type="pil") image_process_mode = gr.Radio( ["Crop", "Resize", "Pad", "Default"], value="Default", label="Preprocess for non-square image", visible=False) if cur_dir is None: cur_dir = os.path.dirname(os.path.abspath(__file__)) gr.Examples(examples=[ [f"{cur_dir}/examples/extreme_ironing.jpg", "What is unusual about this image?"], [f"{cur_dir}/examples/waterview.jpg", "What are the things I should be cautious about when I visit here?"], ], inputs=[imagebox, textbox]) with gr.Accordion("Parameters", open=False) as parameter_row: temperature = gr.Slider(minimum=0.0, maximum=1.0, value=0.2, step=0.1, interactive=True, label="Temperature",) top_p = gr.Slider(minimum=0.0, maximum=1.0, value=0.7, step=0.1, interactive=True, label="Top P",) max_output_tokens = gr.Slider(minimum=0, maximum=1024, value=512, step=64, interactive=True, label="Max output tokens",) with gr.Column(scale=8): chatbot = gr.Chatbot( elem_id="chatbot", label="LLaVA Chatbot", height=650, layout="panel", ) with gr.Row(): with gr.Column(scale=8): textbox.render() with gr.Column(scale=1, min_width=50): submit_btn = gr.Button(value="Send", variant="primary") with gr.Row(elem_id="buttons") as button_row: upvote_btn = gr.Button(value="👍 Upvote", interactive=False) downvote_btn = gr.Button(value="👎 Downvote", interactive=False) flag_btn = gr.Button(value="⚠️ Flag", interactive=False) #stop_btn = gr.Button(value="⏹️ Stop Generation", interactive=False) regenerate_btn = gr.Button(value="🔄 Regenerate", interactive=False) clear_btn = gr.Button(value="🗑️ Clear", interactive=False) if not embed_mode: gr.Markdown(tos_markdown) gr.Markdown(learn_more_markdown) url_params = gr.JSON(visible=False) # Register listeners btn_list = [upvote_btn, downvote_btn, flag_btn, regenerate_btn, clear_btn] upvote_btn.click( upvote_last_response, [state, model_selector], [textbox, upvote_btn, downvote_btn, flag_btn] ) downvote_btn.click( downvote_last_response, [state, model_selector], [textbox, upvote_btn, downvote_btn, flag_btn] ) flag_btn.click( flag_last_response, [state, model_selector], [textbox, upvote_btn, downvote_btn, flag_btn] ) regenerate_btn.click( regenerate, [state, image_process_mode], [state, chatbot, textbox, imagebox] + btn_list ).then( http_bot, [state, model_selector, temperature, top_p, max_output_tokens], [state, chatbot] + btn_list, concurrency_limit=concurrency_count ) clear_btn.click( clear_history, None, [state, chatbot, textbox, imagebox] + btn_list, queue=False ) textbox.submit( add_text, [state, textbox, imagebox, image_process_mode], [state, chatbot, textbox, imagebox] + btn_list, queue=False ).then( http_bot, [state, model_selector, temperature, top_p, max_output_tokens], [state, chatbot] + btn_list, concurrency_limit=concurrency_count ) submit_btn.click( add_text, [state, textbox, imagebox, image_process_mode], [state, chatbot, textbox, imagebox] + btn_list ).then( http_bot, [state, model_selector, temperature, top_p, max_output_tokens], [state, chatbot] + btn_list, concurrency_limit=concurrency_count ) if args.model_list_mode == "once": demo.load( load_demo, [url_params], [state, model_selector], js=get_window_url_params ) elif args.model_list_mode == "reload": demo.load( load_demo_refresh_model_list, None, [state, model_selector], queue=False ) else: raise ValueError(f"Unknown model list mode: {args.model_list_mode}") return demo if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--host", type=str, default="0.0.0.0") parser.add_argument("--port", type=int) parser.add_argument("--controller-url", type=str, default="http://localhost:21001") parser.add_argument("--concurrency-count", type=int, default=16) parser.add_argument("--model-list-mode", type=str, default="once", choices=["once", "reload"]) parser.add_argument("--share", action="store_true") parser.add_argument("--moderate", action="store_true") parser.add_argument("--embed", action="store_true") args = parser.parse_args() logger.info(f"args: {args}") models = get_model_list() logger.info(args) demo = build_demo(args.embed, concurrency_count=args.concurrency_count) demo.queue( api_open=False ).launch( server_name=args.host, server_port=args.port, share=args.share ) ================================================ FILE: llava/serve/model_worker.py ================================================ """ A model worker executes the model. """ import argparse import asyncio import json import time import threading import uuid from fastapi import FastAPI, Request, BackgroundTasks from fastapi.responses import StreamingResponse import requests import torch import uvicorn from functools import partial from llava.constants import WORKER_HEART_BEAT_INTERVAL from llava.utils import (build_logger, server_error_msg, pretty_print_semaphore) from llava.model.builder import load_pretrained_model from llava.mm_utils import process_images, load_image_from_base64, tokenizer_image_token from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from transformers import TextIteratorStreamer from threading import Thread GB = 1 << 30 worker_id = str(uuid.uuid4())[:6] logger = build_logger("model_worker", f"model_worker_{worker_id}.log") global_counter = 0 model_semaphore = None def heart_beat_worker(controller): while True: time.sleep(WORKER_HEART_BEAT_INTERVAL) controller.send_heart_beat() class ModelWorker: def __init__(self, controller_addr, worker_addr, worker_id, no_register, model_path, model_base, model_name, load_8bit, load_4bit, device, use_flash_attn=False): self.controller_addr = controller_addr self.worker_addr = worker_addr self.worker_id = worker_id if model_path.endswith("/"): model_path = model_path[:-1] if model_name is None: model_paths = model_path.split("/") if model_paths[-1].startswith('checkpoint-'): self.model_name = model_paths[-2] + "_" + model_paths[-1] else: self.model_name = model_paths[-1] else: self.model_name = model_name self.device = device logger.info(f"Loading the model {self.model_name} on worker {worker_id} ...") self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model( model_path, model_base, self.model_name, load_8bit, load_4bit, device=self.device, use_flash_attn=use_flash_attn) self.is_multimodal = 'llava' in self.model_name.lower() if not no_register: self.register_to_controller() self.heart_beat_thread = threading.Thread( target=heart_beat_worker, args=(self,), daemon=True) self.heart_beat_thread.start() def register_to_controller(self): logger.info("Register to controller") url = self.controller_addr + "/register_worker" data = { "worker_name": self.worker_addr, "check_heart_beat": True, "worker_status": self.get_status() } r = requests.post(url, json=data) assert r.status_code == 200 def send_heart_beat(self): logger.info(f"Send heart beat. Models: {[self.model_name]}. " f"Semaphore: {pretty_print_semaphore(model_semaphore)}. " f"global_counter: {global_counter}") url = self.controller_addr + "/receive_heart_beat" while True: try: ret = requests.post(url, json={ "worker_name": self.worker_addr, "queue_length": self.get_queue_length()}, timeout=5) exist = ret.json()["exist"] break except requests.exceptions.RequestException as e: logger.error(f"heart beat error: {e}") time.sleep(5) if not exist: self.register_to_controller() def get_queue_length(self): if model_semaphore is None: return 0 else: return args.limit_model_concurrency - model_semaphore._value + (len( model_semaphore._waiters) if model_semaphore._waiters is not None else 0) def get_status(self): return { "model_names": [self.model_name], "speed": 1, "queue_length": self.get_queue_length(), } @torch.inference_mode() def generate_stream(self, params): tokenizer, model, image_processor = self.tokenizer, self.model, self.image_processor prompt = params["prompt"] ori_prompt = prompt images = params.get("images", None) num_image_tokens = 0 if images is not None and len(images) > 0 and self.is_multimodal: if len(images) > 0: if len(images) != prompt.count(DEFAULT_IMAGE_TOKEN): raise ValueError("Number of images does not match number of tokens in prompt") images = [load_image_from_base64(image) for image in images] image_sizes = [image.size for image in images] images = process_images(images, image_processor, model.config) if type(images) is list: images = [image.to(self.model.device, dtype=torch.float16) for image in images] else: images = images.to(self.model.device, dtype=torch.float16) replace_token = DEFAULT_IMAGE_TOKEN if getattr(self.model.config, 'mm_use_im_start_end', False): replace_token = DEFAULT_IM_START_TOKEN + replace_token + DEFAULT_IM_END_TOKEN prompt = prompt.replace(DEFAULT_IMAGE_TOKEN, replace_token) num_image_tokens = prompt.count(replace_token) * model.get_vision_tower().num_patches else: images = None image_sizes = None image_args = {"images": images, "image_sizes": image_sizes} else: images = None image_args = {} temperature = float(params.get("temperature", 1.0)) top_p = float(params.get("top_p", 1.0)) max_context_length = getattr(model.config, 'max_position_embeddings', 2048) max_new_tokens = min(int(params.get("max_new_tokens", 256)), 1024) stop_str = params.get("stop", None) do_sample = True if temperature > 0.001 else False input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(self.device) keywords = [stop_str] # stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids) streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True, timeout=15) max_new_tokens = min(max_new_tokens, max_context_length - input_ids.shape[-1] - num_image_tokens) if max_new_tokens < 1: yield json.dumps({"text": ori_prompt + "Exceeds max token length. Please start a new conversation, thanks.", "error_code": 0}).encode() + b"\0" return thread = Thread(target=model.generate, kwargs=dict( inputs=input_ids, do_sample=do_sample, temperature=temperature, top_p=top_p, max_new_tokens=max_new_tokens, streamer=streamer, use_cache=True, **image_args )) thread.start() generated_text = ori_prompt for new_text in streamer: generated_text += new_text if generated_text.endswith(stop_str): generated_text = generated_text[:-len(stop_str)] yield json.dumps({"text": generated_text, "error_code": 0}).encode() + b"\0" def generate_stream_gate(self, params): try: for x in self.generate_stream(params): yield x except ValueError as e: print("Caught ValueError:", e) ret = { "text": server_error_msg, "error_code": 1, } yield json.dumps(ret).encode() + b"\0" except torch.cuda.CudaError as e: print("Caught torch.cuda.CudaError:", e) ret = { "text": server_error_msg, "error_code": 1, } yield json.dumps(ret).encode() + b"\0" except Exception as e: print("Caught Unknown Error", e) ret = { "text": server_error_msg, "error_code": 1, } yield json.dumps(ret).encode() + b"\0" app = FastAPI() def release_model_semaphore(fn=None): model_semaphore.release() if fn is not None: fn() @app.post("/worker_generate_stream") async def generate_stream(request: Request): global model_semaphore, global_counter global_counter += 1 params = await request.json() if model_semaphore is None: model_semaphore = asyncio.Semaphore(args.limit_model_concurrency) await model_semaphore.acquire() worker.send_heart_beat() generator = worker.generate_stream_gate(params) background_tasks = BackgroundTasks() background_tasks.add_task(partial(release_model_semaphore, fn=worker.send_heart_beat)) return StreamingResponse(generator, background=background_tasks) @app.post("/worker_get_status") async def get_status(request: Request): return worker.get_status() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--host", type=str, default="localhost") parser.add_argument("--port", type=int, default=21002) parser.add_argument("--worker-address", type=str, default="http://localhost:21002") parser.add_argument("--controller-address", type=str, default="http://localhost:21001") parser.add_argument("--model-path", type=str, default="facebook/opt-350m") parser.add_argument("--model-base", type=str, default=None) parser.add_argument("--model-name", type=str) parser.add_argument("--device", type=str, default="cuda") parser.add_argument("--multi-modal", action="store_true", help="Multimodal mode is automatically detected with model name, please make sure `llava` is included in the model path.") parser.add_argument("--limit-model-concurrency", type=int, default=5) parser.add_argument("--stream-interval", type=int, default=1) parser.add_argument("--no-register", action="store_true") parser.add_argument("--load-8bit", action="store_true") parser.add_argument("--load-4bit", action="store_true") parser.add_argument("--use-flash-attn", action="store_true") args = parser.parse_args() logger.info(f"args: {args}") if args.multi_modal: logger.warning("Multimodal mode is automatically detected with model name, please make sure `llava` is included in the model path.") worker = ModelWorker(args.controller_address, args.worker_address, worker_id, args.no_register, args.model_path, args.model_base, args.model_name, args.load_8bit, args.load_4bit, args.device, use_flash_attn=args.use_flash_attn) uvicorn.run(app, host=args.host, port=args.port, log_level="info") ================================================ FILE: llava/serve/register_worker.py ================================================ """ Manually register workers. Usage: python3 -m fastchat.serve.register_worker --controller http://localhost:21001 --worker-name http://localhost:21002 """ import argparse import requests if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--controller-address", type=str) parser.add_argument("--worker-name", type=str) parser.add_argument("--check-heart-beat", action="store_true") args = parser.parse_args() url = args.controller_address + "/register_worker" data = { "worker_name": args.worker_name, "check_heart_beat": args.check_heart_beat, "worker_status": None, } r = requests.post(url, json=data) assert r.status_code == 200 ================================================ FILE: llava/serve/sglang_worker.py ================================================ """ A model worker executes the model. """ import argparse import asyncio from concurrent.futures import ThreadPoolExecutor import json import time import threading import uuid from fastapi import FastAPI, Request, BackgroundTasks from fastapi.responses import StreamingResponse import requests import re import uvicorn from functools import partial from llava.constants import WORKER_HEART_BEAT_INTERVAL from llava.utils import (build_logger, server_error_msg, pretty_print_semaphore) from llava.mm_utils import process_images, load_image_from_base64, tokenizer_image_token, expand2square from llava.constants import DEFAULT_IMAGE_TOKEN import sglang as sgl from sglang.backend.runtime_endpoint import RuntimeEndpoint GB = 1 << 30 worker_id = str(uuid.uuid4())[:6] logger = build_logger("model_worker", f"model_worker_{worker_id}.log") global_counter = 0 model_semaphore = None def heart_beat_worker(controller): while True: time.sleep(WORKER_HEART_BEAT_INTERVAL) controller.send_heart_beat() @sgl.function def pipeline(s, prompt, max_tokens): for p in prompt: if type(p) is str: s += p else: s += sgl.image(p) s += sgl.gen("response", max_tokens=max_tokens) class ModelWorker: def __init__(self, controller_addr, worker_addr, sgl_endpoint, worker_id, no_register, model_name): self.controller_addr = controller_addr self.worker_addr = worker_addr self.worker_id = worker_id # Select backend backend = RuntimeEndpoint(sgl_endpoint) sgl.set_default_backend(backend) model_path = backend.model_info["model_path"] if model_path.endswith("/"): model_path = model_path[:-1] if model_name is None: model_paths = model_path.split("/") if model_paths[-1].startswith('checkpoint-'): self.model_name = model_paths[-2] + "_" + model_paths[-1] else: self.model_name = model_paths[-1] else: self.model_name = model_name logger.info(f"Loading the SGLANG model {self.model_name} on worker {worker_id} ...") if not no_register: self.register_to_controller() self.heart_beat_thread = threading.Thread( target=heart_beat_worker, args=(self,), daemon=True) self.heart_beat_thread.start() def register_to_controller(self): logger.info("Register to controller") url = self.controller_addr + "/register_worker" data = { "worker_name": self.worker_addr, "check_heart_beat": True, "worker_status": self.get_status() } r = requests.post(url, json=data) assert r.status_code == 200 def send_heart_beat(self): logger.info(f"Send heart beat. Models: {[self.model_name]}. " f"Semaphore: {pretty_print_semaphore(model_semaphore)}. " f"global_counter: {global_counter}") url = self.controller_addr + "/receive_heart_beat" while True: try: ret = requests.post(url, json={ "worker_name": self.worker_addr, "queue_length": self.get_queue_length()}, timeout=5) exist = ret.json()["exist"] break except requests.exceptions.RequestException as e: logger.error(f"heart beat error: {e}") time.sleep(5) if not exist: self.register_to_controller() def get_queue_length(self): if model_semaphore is None: return 0 else: return args.limit_model_concurrency - model_semaphore._value + (len( model_semaphore._waiters) if model_semaphore._waiters is not None else 0) def get_status(self): return { "model_names": [self.model_name], "speed": 1, "queue_length": self.get_queue_length(), } async def generate_stream(self, params): ori_prompt = prompt = params["prompt"] images = params.get("images", None) if images is not None and len(images) > 0: if len(images) > 0: if len(images) != prompt.count(DEFAULT_IMAGE_TOKEN): raise ValueError("Number of images does not match number of tokens in prompt") images = [load_image_from_base64(image) for image in images] # FIXME: for image-start/end token # replace_token = DEFAULT_IMAGE_TOKEN # if getattr(self.model.config, 'mm_use_im_start_end', False): # replace_token = DEFAULT_IM_START_TOKEN + replace_token + DEFAULT_IM_END_TOKEN # prompt = prompt.replace(DEFAULT_IMAGE_TOKEN, replace_token) prompt = prompt.replace(' ' + DEFAULT_IMAGE_TOKEN + '\n', DEFAULT_IMAGE_TOKEN) prompt_split = prompt.split(DEFAULT_IMAGE_TOKEN) prompt = [] for i in range(len(prompt_split)): prompt.append(prompt_split[i]) if i < len(images): prompt.append(images[i]) else: prompt = [prompt] temperature = float(params.get("temperature", 1.0)) top_p = float(params.get("top_p", 1.0)) # max_context_length = getattr(model.config, 'max_position_embeddings', 2048) max_new_tokens = min(int(params.get("max_new_tokens", 256)), 1024) stop_str = params.get("stop", None) stop_str = [stop_str] if stop_str is not None else None print({'prompt': prompt, 'max_new_tokens': max_new_tokens, 'temperature': temperature, 'top_p': top_p}) state = pipeline.run(prompt, max_new_tokens, temperature=temperature, top_p=top_p, stream=True) generated_text = ori_prompt async for text_outputs in state.text_async_iter(var_name="response"): generated_text += text_outputs yield json.dumps({"text": generated_text, "error_code": 0}).encode() + b"\0" async def generate_stream_gate(self, params): try: async for x in self.generate_stream(params): yield x except ValueError as e: print("Caught ValueError:", e) ret = { "text": server_error_msg, "error_code": 1, } yield json.dumps(ret).encode() + b"\0" except Exception as e: print("Caught Unknown Error", e) ret = { "text": server_error_msg, "error_code": 1, } yield json.dumps(ret).encode() + b"\0" app = FastAPI() def release_model_semaphore(fn=None): model_semaphore.release() if fn is not None: fn() @app.post("/worker_generate_stream") async def generate_stream(request: Request): global model_semaphore, global_counter global_counter += 1 params = await request.json() if model_semaphore is None: model_semaphore = asyncio.Semaphore(args.limit_model_concurrency) await model_semaphore.acquire() worker.send_heart_beat() generator = worker.generate_stream_gate(params) background_tasks = BackgroundTasks() background_tasks.add_task(partial(release_model_semaphore, fn=worker.send_heart_beat)) return StreamingResponse(generator, background=background_tasks) @app.post("/worker_get_status") async def get_status(request: Request): return worker.get_status() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--host", type=str, default="localhost") parser.add_argument("--port", type=int, default=21002) parser.add_argument("--worker-address", type=str, default="http://localhost:21002") parser.add_argument("--controller-address", type=str, default="http://localhost:21001") parser.add_argument("--model-name", type=str) parser.add_argument("--sgl-endpoint", type=str) parser.add_argument("--limit-model-concurrency", type=int, default=5) parser.add_argument("--stream-interval", type=int, default=1) parser.add_argument("--no-register", action="store_true") args = parser.parse_args() logger.info(f"args: {args}") worker = ModelWorker(args.controller_address, args.worker_address, args.sgl_endpoint, worker_id, args.no_register, args.model_name) uvicorn.run(app, host=args.host, port=args.port, log_level="info") ================================================ FILE: llava/serve/test_message.py ================================================ import argparse import json import requests from llava.conversation import default_conversation def main(): if args.worker_address: worker_addr = args.worker_address else: controller_addr = args.controller_address ret = requests.post(controller_addr + "/refresh_all_workers") ret = requests.post(controller_addr + "/list_models") models = ret.json()["models"] models.sort() print(f"Models: {models}") ret = requests.post(controller_addr + "/get_worker_address", json={"model": args.model_name}) worker_addr = ret.json()["address"] print(f"worker_addr: {worker_addr}") if worker_addr == "": return conv = default_conversation.copy() conv.append_message(conv.roles[0], args.message) prompt = conv.get_prompt() headers = {"User-Agent": "LLaVA Client"} pload = { "model": args.model_name, "prompt": prompt, "max_new_tokens": args.max_new_tokens, "temperature": 0.7, "stop": conv.sep, } response = requests.post(worker_addr + "/worker_generate_stream", headers=headers, json=pload, stream=True) print(prompt.replace(conv.sep, "\n"), end="") for chunk in response.iter_lines(chunk_size=8192, decode_unicode=False, delimiter=b"\0"): if chunk: data = json.loads(chunk.decode("utf-8")) output = data["text"].split(conv.sep)[-1] print(output, end="\r") print("") if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--controller-address", type=str, default="http://localhost:21001") parser.add_argument("--worker-address", type=str) parser.add_argument("--model-name", type=str, default="facebook/opt-350m") parser.add_argument("--max-new-tokens", type=int, default=32) parser.add_argument("--message", type=str, default= "Tell me a story with more than 1000 words.") args = parser.parse_args() main() ================================================ FILE: llava/train/llama_flash_attn_monkey_patch.py ================================================ from typing import Optional, Tuple import warnings import torch import transformers from transformers.models.llama.modeling_llama import apply_rotary_pos_emb, repeat_kv try: from flash_attn.flash_attn_interface import flash_attn_unpadded_qkvpacked_func except ImportError: from flash_attn.flash_attn_interface import flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func from flash_attn.bert_padding import unpad_input, pad_input def forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.Tensor] = None, past_key_value: Optional[Tuple[torch.Tensor]] = None, output_attentions: bool = False, use_cache: bool = False, ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: if output_attentions: warnings.warn( "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead." ) bsz, q_len, _ = hidden_states.size() query_states = ( self.q_proj(hidden_states) .view(bsz, q_len, self.num_heads, self.head_dim) .transpose(1, 2) ) key_states = ( self.k_proj(hidden_states) .view(bsz, q_len, self.num_key_value_heads, self.head_dim) .transpose(1, 2) ) value_states = ( self.v_proj(hidden_states) .view(bsz, q_len, self.num_key_value_heads, self.head_dim) .transpose(1, 2) ) # shape: (b, num_heads, s, head_dim) kv_seq_len = key_states.shape[-2] if past_key_value is not None: kv_seq_len += past_key_value[0].shape[-2] cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len) query_states, key_states = apply_rotary_pos_emb( query_states, key_states, cos, sin, position_ids ) if past_key_value is not None: # reuse k, v key_states = torch.cat([past_key_value[0], key_states], dim=2) value_states = torch.cat([past_key_value[1], value_states], dim=2) past_key_value = (key_states, value_states) if use_cache else None # repeat k/v heads if n_kv_heads < n_heads key_states = repeat_kv(key_states, self.num_key_value_groups) value_states = repeat_kv(value_states, self.num_key_value_groups) # Transform the data into the format required by flash attention qkv = torch.stack([query_states, key_states, value_states], dim=2) qkv = qkv.transpose(1, 3) # shape: [b, s, 3, num_heads, head_dim] key_padding_mask = attention_mask if key_padding_mask is None: qkv = qkv.reshape(-1, 3, self.num_heads, self.head_dim) cu_q_lens = torch.arange( 0, (bsz + 1) * q_len, step=q_len, dtype=torch.int32, device=qkv.device ) max_s = q_len output = flash_attn_unpadded_qkvpacked_func( qkv, cu_q_lens, max_s, 0.0, softmax_scale=None, causal=True ) output = output.view(bsz, q_len, -1) else: qkv = qkv.reshape(bsz, q_len, -1) qkv, indices, cu_q_lens, max_s = unpad_input(qkv, key_padding_mask) qkv = qkv.view(-1, 3, self.num_heads, self.head_dim) output_unpad = flash_attn_unpadded_qkvpacked_func( qkv, cu_q_lens, max_s, 0.0, softmax_scale=None, causal=True ) output_unpad = output_unpad.reshape(-1, self.num_heads * self.head_dim) output = pad_input(output_unpad, indices, bsz, q_len) return self.o_proj(output), None, past_key_value # Disable the transformation of the attention mask in LlamaModel as the flash attention # requires the attention mask to be the same as the key_padding_mask def _prepare_decoder_attention_mask( self, attention_mask, input_shape, inputs_embeds, past_key_values_length ): # [bsz, seq_len] return attention_mask def replace_llama_attn_with_flash_attn(): cuda_major, cuda_minor = torch.cuda.get_device_capability() if cuda_major < 8: warnings.warn( "Flash attention is only supported on A100 or H100 GPU during training due to head dim > 64 backward." "ref: https://github.com/HazyResearch/flash-attention/issues/190#issuecomment-1523359593" ) transformers.models.llama.modeling_llama.LlamaModel._prepare_decoder_attention_mask = ( _prepare_decoder_attention_mask ) transformers.models.llama.modeling_llama.LlamaAttention.forward = forward ================================================ FILE: llava/train/llama_xformers_attn_monkey_patch.py ================================================ """ Directly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments """ import logging import math from typing import Optional, Tuple import torch import transformers.models.llama.modeling_llama from torch import nn try: import xformers.ops except ImportError: logging.error("xformers not found! Please install it before trying to use it.") def replace_llama_attn_with_xformers_attn(): transformers.models.llama.modeling_llama.LlamaAttention.forward = xformers_forward def xformers_forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_value: Optional[Tuple[torch.Tensor]] = None, output_attentions: bool = False, use_cache: bool = False, ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: # pylint: disable=duplicate-code bsz, q_len, _ = hidden_states.size() query_states = ( self.q_proj(hidden_states) .view(bsz, q_len, self.num_heads, self.head_dim) .transpose(1, 2) ) key_states = ( self.k_proj(hidden_states) .view(bsz, q_len, self.num_heads, self.head_dim) .transpose(1, 2) ) value_states = ( self.v_proj(hidden_states) .view(bsz, q_len, self.num_heads, self.head_dim) .transpose(1, 2) ) kv_seq_len = key_states.shape[-2] if past_key_value is not None: kv_seq_len += past_key_value[0].shape[-2] cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len) ( query_states, key_states, ) = transformers.models.llama.modeling_llama.apply_rotary_pos_emb( query_states, key_states, cos, sin, position_ids ) # [bsz, nh, t, hd] if past_key_value is not None: # reuse k, v, self_attention key_states = torch.cat([past_key_value[0], key_states], dim=2) value_states = torch.cat([past_key_value[1], value_states], dim=2) past_key_value = (key_states, value_states) if use_cache else None # We only apply xformers optimizations if we don't need to output the whole attention matrix if not output_attentions: query_states = query_states.transpose(1, 2) key_states = key_states.transpose(1, 2) value_states = value_states.transpose(1, 2) # This is a nasty hack. We know attention_mask in transformers is either LowerTriangular or all Zeros. # We therefore check if one element in the upper triangular portion is zero. If it is, then the mask is all zeros. if attention_mask is None or attention_mask[0, 0, 0, 1] == 0: # input and output should be of form (bsz, q_len, num_heads, head_dim) attn_output = xformers.ops.memory_efficient_attention( query_states, key_states, value_states, attn_bias=None ) else: # input and output should be of form (bsz, q_len, num_heads, head_dim) attn_output = xformers.ops.memory_efficient_attention( query_states, key_states, value_states, attn_bias=xformers.ops.LowerTriangularMask(), ) attn_weights = None else: attn_weights = torch.matmul( query_states, key_states.transpose(2, 3) ) / math.sqrt(self.head_dim) if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len): raise ValueError( f"Attention weights should be of size {(bsz * self.num_heads, q_len, kv_seq_len)}, but is" f" {attn_weights.size()}" ) if attention_mask is not None: if attention_mask.size() != (bsz, 1, q_len, kv_seq_len): raise ValueError( f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}" ) attn_weights = attn_weights + attention_mask attn_weights = torch.max( attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min) ) # upcast attention to fp32 attn_weights = nn.functional.softmax( attn_weights, dim=-1, dtype=torch.float32 ).to(query_states.dtype) attn_output = torch.matmul(attn_weights, value_states) if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim): raise ValueError( f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is" f" {attn_output.size()}" ) attn_output = attn_output.transpose(1, 2) attn_output = attn_output.reshape(bsz, q_len, self.hidden_size) attn_output = self.o_proj(attn_output) return attn_output, attn_weights, past_key_value ================================================ FILE: llava/train/llava_trainer.py ================================================ import os import torch import torch.nn as nn from torch.utils.data import Sampler from transformers import Trainer from transformers.trainer import ( is_sagemaker_mp_enabled, get_parameter_names, has_length, ALL_LAYERNORM_LAYERS, logger, ) from typing import List, Optional def maybe_zero_3(param, ignore_status=False, name=None): from deepspeed import zero from deepspeed.runtime.zero.partition_parameters import ZeroParamStatus if hasattr(param, "ds_id"): if param.ds_status == ZeroParamStatus.NOT_AVAILABLE: if not ignore_status: print(name, 'no ignore status') with zero.GatheredParameters([param]): param = param.data.detach().cpu().clone() else: param = param.detach().cpu().clone() return param def get_mm_adapter_state_maybe_zero_3(named_params, keys_to_match): to_return = {k: t for k, t in named_params if any(key_match in k for key_match in keys_to_match)} to_return = {k: maybe_zero_3(v, ignore_status=True, name=k).cpu() for k, v in to_return.items()} return to_return def split_to_even_chunks(indices, lengths, num_chunks): """ Split a list of indices into `chunks` chunks of roughly equal lengths. """ if len(indices) % num_chunks != 0: return [indices[i::num_chunks] for i in range(num_chunks)] num_indices_per_chunk = len(indices) // num_chunks chunks = [[] for _ in range(num_chunks)] chunks_lengths = [0 for _ in range(num_chunks)] for index in indices: shortest_chunk = chunks_lengths.index(min(chunks_lengths)) chunks[shortest_chunk].append(index) chunks_lengths[shortest_chunk] += lengths[index] if len(chunks[shortest_chunk]) == num_indices_per_chunk: chunks_lengths[shortest_chunk] = float("inf") return chunks def get_modality_length_grouped_indices(lengths, batch_size, world_size, generator=None): # We need to use torch for the random part as a distributed sampler will set the random seed for torch. assert all(l != 0 for l in lengths), "Should not have zero length." if all(l > 0 for l in lengths) or all(l < 0 for l in lengths): # all samples are in the same modality return get_length_grouped_indices(lengths, batch_size, world_size, generator=generator) mm_indices, mm_lengths = zip(*[(i, l) for i, l in enumerate(lengths) if l > 0]) lang_indices, lang_lengths = zip(*[(i, -l) for i, l in enumerate(lengths) if l < 0]) mm_shuffle = [mm_indices[i] for i in get_length_grouped_indices(mm_lengths, batch_size, world_size, generator=None)] lang_shuffle = [lang_indices[i] for i in get_length_grouped_indices(lang_lengths, batch_size, world_size, generator=None)] megabatch_size = world_size * batch_size mm_megabatches = [mm_shuffle[i : i + megabatch_size] for i in range(0, len(mm_shuffle), megabatch_size)] lang_megabatches = [lang_shuffle[i : i + megabatch_size] for i in range(0, len(lang_shuffle), megabatch_size)] last_mm = mm_megabatches[-1] last_lang = lang_megabatches[-1] additional_batch = last_mm + last_lang megabatches = mm_megabatches[:-1] + lang_megabatches[:-1] megabatch_indices = torch.randperm(len(megabatches), generator=generator) megabatches = [megabatches[i] for i in megabatch_indices] if len(additional_batch) > 0: megabatches.append(sorted(additional_batch)) return [i for megabatch in megabatches for i in megabatch] def get_length_grouped_indices(lengths, batch_size, world_size, generator=None, merge=True): # We need to use torch for the random part as a distributed sampler will set the random seed for torch. indices = torch.randperm(len(lengths), generator=generator) megabatch_size = world_size * batch_size megabatches = [indices[i : i + megabatch_size].tolist() for i in range(0, len(lengths), megabatch_size)] megabatches = [sorted(megabatch, key=lambda i: lengths[i], reverse=True) for megabatch in megabatches] megabatches = [split_to_even_chunks(megabatch, lengths, world_size) for megabatch in megabatches] return [i for megabatch in megabatches for batch in megabatch for i in batch] class LengthGroupedSampler(Sampler): r""" Sampler that samples indices in a way that groups together features of the dataset of roughly the same length while keeping a bit of randomness. """ def __init__( self, batch_size: int, world_size: int, lengths: Optional[List[int]] = None, generator=None, group_by_modality: bool = False, ): if lengths is None: raise ValueError("Lengths must be provided.") self.batch_size = batch_size self.world_size = world_size self.lengths = lengths self.generator = generator self.group_by_modality = group_by_modality def __len__(self): return len(self.lengths) def __iter__(self): if self.group_by_modality: indices = get_modality_length_grouped_indices(self.lengths, self.batch_size, self.world_size, generator=self.generator) else: indices = get_length_grouped_indices(self.lengths, self.batch_size, self.world_size, generator=self.generator) return iter(indices) class LLaVATrainer(Trainer): def _get_train_sampler(self) -> Optional[torch.utils.data.Sampler]: if self.train_dataset is None or not has_length(self.train_dataset): return None if self.args.group_by_modality_length: lengths = self.train_dataset.modality_lengths return LengthGroupedSampler( self.args.train_batch_size, world_size=self.args.world_size * self.args.gradient_accumulation_steps, lengths=lengths, group_by_modality=True, ) else: return super()._get_train_sampler() def create_optimizer(self): """ Setup the optimizer. We provide a reasonable default that works well. If you want to use something else, you can pass a tuple in the Trainer's init through `optimizers`, or subclass and override this method in a subclass. """ if is_sagemaker_mp_enabled(): return super().create_optimizer() opt_model = self.model if self.optimizer is None: decay_parameters = get_parameter_names(opt_model, ALL_LAYERNORM_LAYERS) decay_parameters = [name for name in decay_parameters if "bias" not in name] if self.args.mm_projector_lr is not None: projector_parameters = [name for name, _ in opt_model.named_parameters() if "mm_projector" in name] optimizer_grouped_parameters = [ { "params": [ p for n, p in opt_model.named_parameters() if (n in decay_parameters and n not in projector_parameters and p.requires_grad) ], "weight_decay": self.args.weight_decay, }, { "params": [ p for n, p in opt_model.named_parameters() if (n not in decay_parameters and n not in projector_parameters and p.requires_grad) ], "weight_decay": 0.0, }, { "params": [ p for n, p in opt_model.named_parameters() if (n in decay_parameters and n in projector_parameters and p.requires_grad) ], "weight_decay": self.args.weight_decay, "lr": self.args.mm_projector_lr, }, { "params": [ p for n, p in opt_model.named_parameters() if (n not in decay_parameters and n in projector_parameters and p.requires_grad) ], "weight_decay": 0.0, "lr": self.args.mm_projector_lr, }, ] else: optimizer_grouped_parameters = [ { "params": [ p for n, p in opt_model.named_parameters() if (n in decay_parameters and p.requires_grad) ], "weight_decay": self.args.weight_decay, }, { "params": [ p for n, p in opt_model.named_parameters() if (n not in decay_parameters and p.requires_grad) ], "weight_decay": 0.0, }, ] optimizer_cls, optimizer_kwargs = Trainer.get_optimizer_cls_and_kwargs(self.args) self.optimizer = optimizer_cls(optimizer_grouped_parameters, **optimizer_kwargs) if optimizer_cls.__name__ == "Adam8bit": import bitsandbytes manager = bitsandbytes.optim.GlobalOptimManager.get_instance() skipped = 0 for module in opt_model.modules(): if isinstance(module, nn.Embedding): skipped += sum({p.data_ptr(): p.numel() for p in module.parameters()}.values()) logger.info(f"skipped {module}: {skipped/2**20}M params") manager.register_module_override(module, "weight", {"optim_bits": 32}) logger.debug(f"bitsandbytes: will optimize {module} in fp32") logger.info(f"skipped: {skipped/2**20}M params") return self.optimizer def _save_checkpoint(self, model, trial, metrics=None): if getattr(self.args, 'tune_mm_mlp_adapter', False): from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR checkpoint_folder = f"{PREFIX_CHECKPOINT_DIR}-{self.state.global_step}" run_dir = self._get_output_dir(trial=trial) output_dir = os.path.join(run_dir, checkpoint_folder) # Only save Adapter keys_to_match = ['mm_projector', 'vision_resampler'] if getattr(self.args, "use_im_start_end", False): keys_to_match.extend(['embed_tokens', 'embed_in']) weight_to_save = get_mm_adapter_state_maybe_zero_3(self.model.named_parameters(), keys_to_match) if self.args.local_rank == 0 or self.args.local_rank == -1: self.model.config.save_pretrained(output_dir) torch.save(weight_to_save, os.path.join(output_dir, f'mm_projector.bin')) else: super(LLaVATrainer, self)._save_checkpoint(model, trial, metrics) def _save(self, output_dir: Optional[str] = None, state_dict=None): if getattr(self.args, 'tune_mm_mlp_adapter', False): pass else: super(LLaVATrainer, self)._save(output_dir, state_dict) ================================================ FILE: llava/train/train.py ================================================ # Adopted from https://github.com/lm-sys/FastChat. Below is the original copyright: # Adopted from tatsu-lab@stanford_alpaca. Below is the original copyright: # Copyright 2023 Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. import os import copy from dataclasses import dataclass, field import json import logging import pathlib from typing import Dict, Optional, Sequence, List import torch import transformers import tokenizers from llava.constants import IGNORE_INDEX, IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN from torch.utils.data import Dataset from llava.train.llava_trainer import LLaVATrainer from llava import conversation as conversation_lib from llava.model import * from llava.mm_utils import tokenizer_image_token from PIL import Image local_rank = None def rank0_print(*args): if local_rank == 0: print(*args) from packaging import version IS_TOKENIZER_GREATER_THAN_0_14 = version.parse(tokenizers.__version__) >= version.parse('0.14') @dataclass class ModelArguments: model_name_or_path: Optional[str] = field(default="facebook/opt-125m") version: Optional[str] = field(default="v0") freeze_backbone: bool = field(default=False) tune_mm_mlp_adapter: bool = field(default=False) vision_tower: Optional[str] = field(default=None) mm_vision_select_layer: Optional[int] = field(default=-1) # default to the last layer pretrain_mm_mlp_adapter: Optional[str] = field(default=None) mm_projector_type: Optional[str] = field(default='linear') mm_use_im_start_end: bool = field(default=False) mm_use_im_patch_token: bool = field(default=True) mm_patch_merge_type: Optional[str] = field(default='flat') mm_vision_select_feature: Optional[str] = field(default="patch") @dataclass class DataArguments: data_path: str = field(default=None, metadata={"help": "Path to the training data."}) lazy_preprocess: bool = False is_multimodal: bool = False image_folder: Optional[str] = field(default=None) image_aspect_ratio: str = 'square' @dataclass class TrainingArguments(transformers.TrainingArguments): cache_dir: Optional[str] = field(default=None) optim: str = field(default="adamw_torch") remove_unused_columns: bool = field(default=False) freeze_mm_mlp_adapter: bool = field(default=False) mpt_attn_impl: Optional[str] = field(default="triton") model_max_length: int = field( default=512, metadata={ "help": "Maximum sequence length. Sequences will be right padded (and possibly truncated)." }, ) double_quant: bool = field( default=True, metadata={"help": "Compress the quantization statistics through double quantization."} ) quant_type: str = field( default="nf4", metadata={"help": "Quantization data type to use. Should be one of `fp4` or `nf4`."} ) bits: int = field( default=16, metadata={"help": "How many bits to use."} ) lora_enable: bool = False lora_r: int = 64 lora_alpha: int = 16 lora_dropout: float = 0.05 lora_weight_path: str = "" lora_bias: str = "none" mm_projector_lr: Optional[float] = None group_by_modality_length: bool = field(default=False) def maybe_zero_3(param, ignore_status=False, name=None): from deepspeed import zero from deepspeed.runtime.zero.partition_parameters import ZeroParamStatus if hasattr(param, "ds_id"): if param.ds_status == ZeroParamStatus.NOT_AVAILABLE: if not ignore_status: logging.warning(f"{name}: param.ds_status != ZeroParamStatus.NOT_AVAILABLE: {param.ds_status}") with zero.GatheredParameters([param]): param = param.data.detach().cpu().clone() else: param = param.detach().cpu().clone() return param # Borrowed from peft.utils.get_peft_model_state_dict def get_peft_state_maybe_zero_3(named_params, bias): if bias == "none": to_return = {k: t for k, t in named_params if "lora_" in k} elif bias == "all": to_return = {k: t for k, t in named_params if "lora_" in k or "bias" in k} elif bias == "lora_only": to_return = {} maybe_lora_bias = {} lora_bias_names = set() for k, t in named_params: if "lora_" in k: to_return[k] = t bias_name = k.split("lora_")[0] + "bias" lora_bias_names.add(bias_name) elif "bias" in k: maybe_lora_bias[k] = t for k, t in maybe_lora_bias: if bias_name in lora_bias_names: to_return[bias_name] = t else: raise NotImplementedError to_return = {k: maybe_zero_3(v, ignore_status=True) for k, v in to_return.items()} return to_return def get_peft_state_non_lora_maybe_zero_3(named_params, require_grad_only=True): to_return = {k: t for k, t in named_params if "lora_" not in k} if require_grad_only: to_return = {k: t for k, t in to_return.items() if t.requires_grad} to_return = {k: maybe_zero_3(v, ignore_status=True).cpu() for k, v in to_return.items()} return to_return def get_mm_adapter_state_maybe_zero_3(named_params, keys_to_match): to_return = {k: t for k, t in named_params if any(key_match in k for key_match in keys_to_match)} to_return = {k: maybe_zero_3(v, ignore_status=True).cpu() for k, v in to_return.items()} return to_return def find_all_linear_names(model): cls = torch.nn.Linear lora_module_names = set() multimodal_keywords = ['mm_projector', 'vision_tower', 'vision_resampler'] for name, module in model.named_modules(): if any(mm_keyword in name for mm_keyword in multimodal_keywords): continue if isinstance(module, cls): names = name.split('.') lora_module_names.add(names[0] if len(names) == 1 else names[-1]) if 'lm_head' in lora_module_names: # needed for 16-bit lora_module_names.remove('lm_head') return list(lora_module_names) def safe_save_model_for_hf_trainer(trainer: transformers.Trainer, output_dir: str): """Collects the state dict and dump to disk.""" if getattr(trainer.args, "tune_mm_mlp_adapter", False): # Only save Adapter keys_to_match = ['mm_projector'] if getattr(trainer.args, "use_im_start_end", False): keys_to_match.extend(['embed_tokens', 'embed_in']) weight_to_save = get_mm_adapter_state_maybe_zero_3(trainer.model.named_parameters(), keys_to_match) trainer.model.config.save_pretrained(output_dir) current_folder = output_dir.split('/')[-1] parent_folder = os.path.dirname(output_dir) if trainer.args.local_rank == 0 or trainer.args.local_rank == -1: if current_folder.startswith('checkpoint-'): mm_projector_folder = os.path.join(parent_folder, "mm_projector") os.makedirs(mm_projector_folder, exist_ok=True) torch.save(weight_to_save, os.path.join(mm_projector_folder, f'{current_folder}.bin')) else: torch.save(weight_to_save, os.path.join(output_dir, f'mm_projector.bin')) return if trainer.deepspeed: torch.cuda.synchronize() trainer.save_model(output_dir) return state_dict = trainer.model.state_dict() if trainer.args.should_save: cpu_state_dict = { key: value.cpu() for key, value in state_dict.items() } del state_dict trainer._save(output_dir, state_dict=cpu_state_dict) # noqa def smart_tokenizer_and_embedding_resize( special_tokens_dict: Dict, tokenizer: transformers.PreTrainedTokenizer, model: transformers.PreTrainedModel, ): """Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64. """ num_new_tokens = tokenizer.add_special_tokens(special_tokens_dict) model.resize_token_embeddings(len(tokenizer)) if num_new_tokens > 0: input_embeddings = model.get_input_embeddings().weight.data output_embeddings = model.get_output_embeddings().weight.data input_embeddings_avg = input_embeddings[:-num_new_tokens].mean( dim=0, keepdim=True) output_embeddings_avg = output_embeddings[:-num_new_tokens].mean( dim=0, keepdim=True) input_embeddings[-num_new_tokens:] = input_embeddings_avg output_embeddings[-num_new_tokens:] = output_embeddings_avg def _tokenize_fn(strings: Sequence[str], tokenizer: transformers.PreTrainedTokenizer) -> Dict: """Tokenize a list of strings.""" tokenized_list = [ tokenizer( text, return_tensors="pt", padding="longest", max_length=tokenizer.model_max_length, truncation=True, ) for text in strings ] input_ids = labels = [ tokenized.input_ids[0] for tokenized in tokenized_list ] input_ids_lens = labels_lens = [ tokenized.input_ids.ne(tokenizer.pad_token_id).sum().item() for tokenized in tokenized_list ] return dict( input_ids=input_ids, labels=labels, input_ids_lens=input_ids_lens, labels_lens=labels_lens, ) def _mask_targets(target, tokenized_lens, speakers): # cur_idx = 0 cur_idx = tokenized_lens[0] tokenized_lens = tokenized_lens[1:] target[:cur_idx] = IGNORE_INDEX for tokenized_len, speaker in zip(tokenized_lens, speakers): if speaker == "human": target[cur_idx+2:cur_idx + tokenized_len] = IGNORE_INDEX cur_idx += tokenized_len def _add_speaker_and_signal(header, source, get_conversation=True): """Add speaker and start/end signal on each round.""" BEGIN_SIGNAL = "### " END_SIGNAL = "\n" conversation = header for sentence in source: from_str = sentence["from"] if from_str.lower() == "human": from_str = conversation_lib.default_conversation.roles[0] elif from_str.lower() == "gpt": from_str = conversation_lib.default_conversation.roles[1] else: from_str = 'unknown' sentence["value"] = (BEGIN_SIGNAL + from_str + ": " + sentence["value"] + END_SIGNAL) if get_conversation: conversation += sentence["value"] conversation += BEGIN_SIGNAL return conversation def preprocess_multimodal( sources: Sequence[str], data_args: DataArguments ) -> Dict: is_multimodal = data_args.is_multimodal if not is_multimodal: return sources for source in sources: for sentence in source: if DEFAULT_IMAGE_TOKEN in sentence['value']: sentence['value'] = sentence['value'].replace(DEFAULT_IMAGE_TOKEN, '').strip() sentence['value'] = DEFAULT_IMAGE_TOKEN + '\n' + sentence['value'] sentence['value'] = sentence['value'].strip() if "mmtag" in conversation_lib.default_conversation.version: sentence['value'] = sentence['value'].replace(DEFAULT_IMAGE_TOKEN, '' + DEFAULT_IMAGE_TOKEN + '') replace_token = DEFAULT_IMAGE_TOKEN if data_args.mm_use_im_start_end: replace_token = DEFAULT_IM_START_TOKEN + replace_token + DEFAULT_IM_END_TOKEN sentence["value"] = sentence["value"].replace(DEFAULT_IMAGE_TOKEN, replace_token) return sources def preprocess_llama_2( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False ) -> Dict: conv = conversation_lib.default_conversation.copy() roles = {"human": conv.roles[0], "gpt": conv.roles[1]} # Apply prompt templates conversations = [] for i, source in enumerate(sources): if roles[source[0]["from"]] != conv.roles[0]: # Skip the first one if it is not from human source = source[1:] conv.messages = [] for j, sentence in enumerate(source): role = roles[sentence["from"]] assert role == conv.roles[j % 2], f"{i}" conv.append_message(role, sentence["value"]) conversations.append(conv.get_prompt()) # Tokenize conversations if has_image: input_ids = torch.stack([tokenizer_image_token(prompt, tokenizer, return_tensors='pt') for prompt in conversations], dim=0) else: input_ids = tokenizer( conversations, return_tensors="pt", padding="longest", max_length=tokenizer.model_max_length, truncation=True, ).input_ids targets = input_ids.clone() assert conv.sep_style == conversation_lib.SeparatorStyle.LLAMA_2 # Mask targets sep = "[/INST] " for conversation, target in zip(conversations, targets): total_len = int(target.ne(tokenizer.pad_token_id).sum()) rounds = conversation.split(conv.sep2) cur_len = 1 target[:cur_len] = IGNORE_INDEX for i, rou in enumerate(rounds): if rou == "": break parts = rou.split(sep) if len(parts) != 2: break parts[0] += sep if has_image: round_len = len(tokenizer_image_token(rou, tokenizer)) instruction_len = len(tokenizer_image_token(parts[0], tokenizer)) - 2 else: round_len = len(tokenizer(rou).input_ids) instruction_len = len(tokenizer(parts[0]).input_ids) - 2 target[cur_len : cur_len + instruction_len] = IGNORE_INDEX cur_len += round_len target[cur_len:] = IGNORE_INDEX if cur_len < tokenizer.model_max_length: if cur_len != total_len: target[:] = IGNORE_INDEX print( f"WARNING: tokenization mismatch: {cur_len} vs. {total_len}." f" (ignored)" ) return dict( input_ids=input_ids, labels=targets, ) def preprocess_v1( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False ) -> Dict: conv = conversation_lib.default_conversation.copy() roles = {"human": conv.roles[0], "gpt": conv.roles[1]} # Apply prompt templates conversations = [] for i, source in enumerate(sources): if roles[source[0]["from"]] != conv.roles[0]: # Skip the first one if it is not from human source = source[1:] conv.messages = [] for j, sentence in enumerate(source): role = roles[sentence["from"]] assert role == conv.roles[j % 2], f"{i}" conv.append_message(role, sentence["value"]) conversations.append(conv.get_prompt()) # Tokenize conversations if has_image: input_ids = torch.stack([tokenizer_image_token(prompt, tokenizer, return_tensors='pt') for prompt in conversations], dim=0) else: input_ids = tokenizer( conversations, return_tensors="pt", padding="longest", max_length=tokenizer.model_max_length, truncation=True, ).input_ids targets = input_ids.clone() assert conv.sep_style == conversation_lib.SeparatorStyle.TWO # Mask targets sep = conv.sep + conv.roles[1] + ": " for conversation, target in zip(conversations, targets): total_len = int(target.ne(tokenizer.pad_token_id).sum()) rounds = conversation.split(conv.sep2) cur_len = 1 target[:cur_len] = IGNORE_INDEX for i, rou in enumerate(rounds): if rou == "": break parts = rou.split(sep) if len(parts) != 2: break parts[0] += sep if has_image: round_len = len(tokenizer_image_token(rou, tokenizer)) instruction_len = len(tokenizer_image_token(parts[0], tokenizer)) - 2 else: round_len = len(tokenizer(rou).input_ids) instruction_len = len(tokenizer(parts[0]).input_ids) - 2 if i != 0 and not tokenizer.legacy and IS_TOKENIZER_GREATER_THAN_0_14: round_len -= 1 instruction_len -= 1 target[cur_len : cur_len + instruction_len] = IGNORE_INDEX cur_len += round_len target[cur_len:] = IGNORE_INDEX if cur_len < tokenizer.model_max_length: if cur_len != total_len: target[:] = IGNORE_INDEX print( f"WARNING: tokenization mismatch: {cur_len} vs. {total_len}." f" (ignored)" ) return dict( input_ids=input_ids, labels=targets, ) def preprocess_mpt( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False ) -> Dict: conv = conversation_lib.default_conversation.copy() roles = {"human": conv.roles[0], "gpt": conv.roles[1]} # Apply prompt templates conversations = [] for i, source in enumerate(sources): if roles[source[0]["from"]] != conv.roles[0]: # Skip the first one if it is not from human source = source[1:] conv.messages = [] for j, sentence in enumerate(source): role = roles[sentence["from"]] assert role == conv.roles[j % 2], f"{i}" conv.append_message(role, sentence["value"]) conversations.append(conv.get_prompt()) # Tokenize conversations if has_image: input_ids = torch.stack([tokenizer_image_token(prompt, tokenizer, return_tensors='pt') for prompt in conversations], dim=0) else: input_ids = tokenizer( conversations, return_tensors="pt", padding="longest", max_length=tokenizer.model_max_length, truncation=True, ).input_ids targets = input_ids.clone() assert conv.sep_style == conversation_lib.SeparatorStyle.MPT # Mask targets sep = conv.sep + conv.roles[1] for conversation, target in zip(conversations, targets): total_len = int(target.ne(tokenizer.pad_token_id).sum()) rounds = conversation.split(conv.sep) re_rounds = [conv.sep.join(rounds[:3])] # system + user + gpt for conv_idx in range(3, len(rounds), 2): re_rounds.append(conv.sep.join(rounds[conv_idx:conv_idx+2])) # user + gpt cur_len = 0 target[:cur_len] = IGNORE_INDEX for i, rou in enumerate(re_rounds): if rou == "": break parts = rou.split(sep) if len(parts) != 2: break parts[0] += sep if has_image: round_len = len(tokenizer_image_token(rou, tokenizer)) instruction_len = len(tokenizer_image_token(parts[0], tokenizer)) - 1 else: round_len = len(tokenizer(rou).input_ids) instruction_len = len(tokenizer(parts[0]).input_ids) - 1 if i != 0 and getattr(tokenizer, 'legacy', False) and IS_TOKENIZER_GREATER_THAN_0_14: round_len += 1 instruction_len += 1 target[cur_len : cur_len + instruction_len] = IGNORE_INDEX cur_len += round_len target[cur_len:] = IGNORE_INDEX if cur_len < tokenizer.model_max_length: if cur_len != total_len: target[:] = IGNORE_INDEX print( f"WARNING: tokenization mismatch: {cur_len} vs. {total_len}." f" (ignored)" ) return dict( input_ids=input_ids, labels=targets, ) def preprocess_plain( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, ) -> Dict: # add end signal and concatenate together conversations = [] for source in sources: assert len(source) == 2 assert DEFAULT_IMAGE_TOKEN in source[0]['value'] source[0]['value'] = DEFAULT_IMAGE_TOKEN conversation = source[0]['value'] + source[1]['value'] + conversation_lib.default_conversation.sep conversations.append(conversation) # tokenize conversations input_ids = [tokenizer_image_token(prompt, tokenizer, return_tensors='pt') for prompt in conversations] targets = copy.deepcopy(input_ids) for target, source in zip(targets, sources): tokenized_len = len(tokenizer_image_token(source[0]['value'], tokenizer)) target[:tokenized_len] = IGNORE_INDEX return dict(input_ids=input_ids, labels=targets) def preprocess( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False ) -> Dict: """ Given a list of sources, each is a conversation list. This transform: 1. Add signal '### ' at the beginning each sentence, with end signal '\n'; 2. Concatenate conversations together; 3. Tokenize the concatenated conversation; 4. Make a deepcopy as the target. Mask human words with IGNORE_INDEX. """ if conversation_lib.default_conversation.sep_style == conversation_lib.SeparatorStyle.PLAIN: return preprocess_plain(sources, tokenizer) if conversation_lib.default_conversation.sep_style == conversation_lib.SeparatorStyle.LLAMA_2: return preprocess_llama_2(sources, tokenizer, has_image=has_image) if conversation_lib.default_conversation.version.startswith("v1"): return preprocess_v1(sources, tokenizer, has_image=has_image) if conversation_lib.default_conversation.version == "mpt": return preprocess_mpt(sources, tokenizer, has_image=has_image) # add end signal and concatenate together conversations = [] for source in sources: header = f"{conversation_lib.default_conversation.system}\n\n" conversation = _add_speaker_and_signal(header, source) conversations.append(conversation) # tokenize conversations def get_tokenize_len(prompts): return [len(tokenizer_image_token(prompt, tokenizer)) for prompt in prompts] if has_image: input_ids = [tokenizer_image_token(prompt, tokenizer, return_tensors='pt') for prompt in conversations] else: conversations_tokenized = _tokenize_fn(conversations, tokenizer) input_ids = conversations_tokenized["input_ids"] targets = copy.deepcopy(input_ids) for target, source in zip(targets, sources): if has_image: tokenized_lens = get_tokenize_len([header] + [s["value"] for s in source]) else: tokenized_lens = _tokenize_fn([header] + [s["value"] for s in source], tokenizer)["input_ids_lens"] speakers = [sentence["from"] for sentence in source] _mask_targets(target, tokenized_lens, speakers) return dict(input_ids=input_ids, labels=targets) class LazySupervisedDataset(Dataset): """Dataset for supervised fine-tuning.""" def __init__(self, data_path: str, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments): super(LazySupervisedDataset, self).__init__() list_data_dict = json.load(open(data_path, "r")) rank0_print("Formatting inputs...Skip in lazy mode") self.tokenizer = tokenizer self.list_data_dict = list_data_dict self.data_args = data_args def __len__(self): return len(self.list_data_dict) @property def lengths(self): length_list = [] for sample in self.list_data_dict: img_tokens = 128 if 'image' in sample else 0 length_list.append(sum(len(conv['value'].split()) for conv in sample['conversations']) + img_tokens) return length_list @property def modality_lengths(self): length_list = [] for sample in self.list_data_dict: cur_len = sum(len(conv['value'].split()) for conv in sample['conversations']) cur_len = cur_len if 'image' in sample else -cur_len length_list.append(cur_len) return length_list def __getitem__(self, i) -> Dict[str, torch.Tensor]: sources = self.list_data_dict[i] if isinstance(i, int): sources = [sources] assert len(sources) == 1, "Don't know why it is wrapped to a list" # FIXME if 'image' in sources[0]: image_file = self.list_data_dict[i]['image'] image_folder = self.data_args.image_folder processor = self.data_args.image_processor image = Image.open(os.path.join(image_folder, image_file)).convert('RGB') if self.data_args.image_aspect_ratio == 'pad': def expand2square(pil_img, background_color): width, height = pil_img.size if width == height: return pil_img elif width > height: result = Image.new(pil_img.mode, (width, width), background_color) result.paste(pil_img, (0, (width - height) // 2)) return result else: result = Image.new(pil_img.mode, (height, height), background_color) result.paste(pil_img, ((height - width) // 2, 0)) return result image = expand2square(image, tuple(int(x*255) for x in processor.image_mean)) image = processor.preprocess(image, return_tensors='pt')['pixel_values'][0] else: image = processor.preprocess(image, return_tensors='pt')['pixel_values'][0] sources = preprocess_multimodal( copy.deepcopy([e["conversations"] for e in sources]), self.data_args) else: sources = copy.deepcopy([e["conversations"] for e in sources]) data_dict = preprocess( sources, self.tokenizer, has_image=('image' in self.list_data_dict[i])) if isinstance(i, int): data_dict = dict(input_ids=data_dict["input_ids"][0], labels=data_dict["labels"][0]) # image exist in the data if 'image' in self.list_data_dict[i]: data_dict['image'] = image elif self.data_args.is_multimodal: # image does not exist in the data, but the model is multimodal crop_size = self.data_args.image_processor.crop_size data_dict['image'] = torch.zeros(3, crop_size['height'], crop_size['width']) return data_dict @dataclass class DataCollatorForSupervisedDataset(object): """Collate examples for supervised fine-tuning.""" tokenizer: transformers.PreTrainedTokenizer def __call__(self, instances: Sequence[Dict]) -> Dict[str, torch.Tensor]: input_ids, labels = tuple([instance[key] for instance in instances] for key in ("input_ids", "labels")) input_ids = torch.nn.utils.rnn.pad_sequence( input_ids, batch_first=True, padding_value=self.tokenizer.pad_token_id) labels = torch.nn.utils.rnn.pad_sequence(labels, batch_first=True, padding_value=IGNORE_INDEX) input_ids = input_ids[:, :self.tokenizer.model_max_length] labels = labels[:, :self.tokenizer.model_max_length] batch = dict( input_ids=input_ids, labels=labels, attention_mask=input_ids.ne(self.tokenizer.pad_token_id), ) if 'image' in instances[0]: images = [instance['image'] for instance in instances] if all(x is not None and x.shape == images[0].shape for x in images): batch['images'] = torch.stack(images) else: batch['images'] = images return batch def make_supervised_data_module(tokenizer: transformers.PreTrainedTokenizer, data_args) -> Dict: """Make dataset and collator for supervised fine-tuning.""" train_dataset = LazySupervisedDataset(tokenizer=tokenizer, data_path=data_args.data_path, data_args=data_args) data_collator = DataCollatorForSupervisedDataset(tokenizer=tokenizer) return dict(train_dataset=train_dataset, eval_dataset=None, data_collator=data_collator) def train(attn_implementation=None): global local_rank parser = transformers.HfArgumentParser( (ModelArguments, DataArguments, TrainingArguments)) model_args, data_args, training_args = parser.parse_args_into_dataclasses() local_rank = training_args.local_rank compute_dtype = (torch.float16 if training_args.fp16 else (torch.bfloat16 if training_args.bf16 else torch.float32)) bnb_model_from_pretrained_args = {} if training_args.bits in [4, 8]: from transformers import BitsAndBytesConfig bnb_model_from_pretrained_args.update(dict( device_map={"": training_args.device}, load_in_4bit=training_args.bits == 4, load_in_8bit=training_args.bits == 8, quantization_config=BitsAndBytesConfig( load_in_4bit=training_args.bits == 4, load_in_8bit=training_args.bits == 8, llm_int8_skip_modules=["mm_projector"], llm_int8_threshold=6.0, llm_int8_has_fp16_weight=False, bnb_4bit_compute_dtype=compute_dtype, bnb_4bit_use_double_quant=training_args.double_quant, bnb_4bit_quant_type=training_args.quant_type # {'fp4', 'nf4'} ) )) if model_args.vision_tower is not None: if 'mpt' in model_args.model_name_or_path: config = transformers.AutoConfig.from_pretrained(model_args.model_name_or_path, trust_remote_code=True) config.attn_config['attn_impl'] = training_args.mpt_attn_impl model = LlavaMptForCausalLM.from_pretrained( model_args.model_name_or_path, config=config, cache_dir=training_args.cache_dir, **bnb_model_from_pretrained_args ) else: model = LlavaLlamaForCausalLM.from_pretrained( model_args.model_name_or_path, cache_dir=training_args.cache_dir, attn_implementation=attn_implementation, torch_dtype=(torch.bfloat16 if training_args.bf16 else None), **bnb_model_from_pretrained_args ) else: model = transformers.LlamaForCausalLM.from_pretrained( model_args.model_name_or_path, cache_dir=training_args.cache_dir, attn_implementation=attn_implementation, torch_dtype=(torch.bfloat16 if training_args.bf16 else None), **bnb_model_from_pretrained_args ) model.config.use_cache = False if model_args.freeze_backbone: model.model.requires_grad_(False) if training_args.bits in [4, 8]: from peft import prepare_model_for_kbit_training model.config.torch_dtype=(torch.float32 if training_args.fp16 else (torch.bfloat16 if training_args.bf16 else torch.float32)) model = prepare_model_for_kbit_training(model, use_gradient_checkpointing=training_args.gradient_checkpointing) if training_args.gradient_checkpointing: if hasattr(model, "enable_input_require_grads"): model.enable_input_require_grads() else: def make_inputs_require_grad(module, input, output): output.requires_grad_(True) model.get_input_embeddings().register_forward_hook(make_inputs_require_grad) if training_args.lora_enable: from peft import LoraConfig, get_peft_model lora_config = LoraConfig( r=training_args.lora_r, lora_alpha=training_args.lora_alpha, target_modules=find_all_linear_names(model), lora_dropout=training_args.lora_dropout, bias=training_args.lora_bias, task_type="CAUSAL_LM", ) if training_args.bits == 16: if training_args.bf16: model.to(torch.bfloat16) if training_args.fp16: model.to(torch.float16) rank0_print("Adding LoRA adapters...") model = get_peft_model(model, lora_config) if 'mpt' in model_args.model_name_or_path: tokenizer = transformers.AutoTokenizer.from_pretrained( model_args.model_name_or_path, cache_dir=training_args.cache_dir, model_max_length=training_args.model_max_length, padding_side="right" ) else: tokenizer = transformers.AutoTokenizer.from_pretrained( model_args.model_name_or_path, cache_dir=training_args.cache_dir, model_max_length=training_args.model_max_length, padding_side="right", use_fast=False, ) if model_args.version == "v0": if tokenizer.pad_token is None: smart_tokenizer_and_embedding_resize( special_tokens_dict=dict(pad_token="[PAD]"), tokenizer=tokenizer, model=model, ) elif model_args.version == "v0.5": tokenizer.pad_token = tokenizer.unk_token else: tokenizer.pad_token = tokenizer.unk_token if model_args.version in conversation_lib.conv_templates: conversation_lib.default_conversation = conversation_lib.conv_templates[model_args.version] else: conversation_lib.default_conversation = conversation_lib.conv_templates["vicuna_v1"] if model_args.vision_tower is not None: model.get_model().initialize_vision_modules( model_args=model_args, fsdp=training_args.fsdp ) vision_tower = model.get_vision_tower() vision_tower.to(dtype=torch.bfloat16 if training_args.bf16 else torch.float16, device=training_args.device) data_args.image_processor = vision_tower.image_processor data_args.is_multimodal = True model.config.image_aspect_ratio = data_args.image_aspect_ratio model.config.tokenizer_padding_side = tokenizer.padding_side model.config.tokenizer_model_max_length = tokenizer.model_max_length model.config.tune_mm_mlp_adapter = training_args.tune_mm_mlp_adapter = model_args.tune_mm_mlp_adapter if model_args.tune_mm_mlp_adapter: model.requires_grad_(False) for p in model.get_model().mm_projector.parameters(): p.requires_grad = True model.config.freeze_mm_mlp_adapter = training_args.freeze_mm_mlp_adapter if training_args.freeze_mm_mlp_adapter: for p in model.get_model().mm_projector.parameters(): p.requires_grad = False if training_args.bits in [4, 8]: model.get_model().mm_projector.to(dtype=compute_dtype, device=training_args.device) model.config.mm_use_im_start_end = data_args.mm_use_im_start_end = model_args.mm_use_im_start_end model.config.mm_projector_lr = training_args.mm_projector_lr training_args.use_im_start_end = model_args.mm_use_im_start_end model.config.mm_use_im_patch_token = model_args.mm_use_im_patch_token model.initialize_vision_tokenizer(model_args, tokenizer=tokenizer) if training_args.bits in [4, 8]: from peft.tuners.lora import LoraLayer for name, module in model.named_modules(): if isinstance(module, LoraLayer): if training_args.bf16: module = module.to(torch.bfloat16) if 'norm' in name: module = module.to(torch.float32) if 'lm_head' in name or 'embed_tokens' in name: if hasattr(module, 'weight'): if training_args.bf16 and module.weight.dtype == torch.float32: module = module.to(torch.bfloat16) data_module = make_supervised_data_module(tokenizer=tokenizer, data_args=data_args) trainer = LLaVATrainer(model=model, tokenizer=tokenizer, args=training_args, **data_module) if list(pathlib.Path(training_args.output_dir).glob("checkpoint-*")): trainer.train(resume_from_checkpoint=True) else: trainer.train() trainer.save_state() model.config.use_cache = True if training_args.lora_enable: state_dict = get_peft_state_maybe_zero_3( model.named_parameters(), training_args.lora_bias ) non_lora_state_dict = get_peft_state_non_lora_maybe_zero_3( model.named_parameters() ) if training_args.local_rank == 0 or training_args.local_rank == -1: model.config.save_pretrained(training_args.output_dir) model.save_pretrained(training_args.output_dir, state_dict=state_dict) torch.save(non_lora_state_dict, os.path.join(training_args.output_dir, 'non_lora_trainables.bin')) else: safe_save_model_for_hf_trainer(trainer=trainer, output_dir=training_args.output_dir) if __name__ == "__main__": train() ================================================ FILE: llava/train/train_mem.py ================================================ from llava.train.train import train if __name__ == "__main__": train(attn_implementation="flash_attention_2") ================================================ FILE: llava/train/train_xformers.py ================================================ # Make it more memory efficient by monkey patching the LLaMA model with xformers attention. # Need to call this before importing transformers. from llava.train.llama_xformers_attn_monkey_patch import ( replace_llama_attn_with_xformers_attn, ) replace_llama_attn_with_xformers_attn() from llava.train.train import train if __name__ == "__main__": train() ================================================ FILE: llava/utils.py ================================================ import datetime import logging import logging.handlers import os import sys import requests from llava.constants import LOGDIR server_error_msg = "**NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.**" moderation_msg = "YOUR INPUT VIOLATES OUR CONTENT MODERATION GUIDELINES. PLEASE TRY AGAIN." handler = None def build_logger(logger_name, logger_filename): global handler formatter = logging.Formatter( fmt="%(asctime)s | %(levelname)s | %(name)s | %(message)s", datefmt="%Y-%m-%d %H:%M:%S", ) # Set the format of root handlers if not logging.getLogger().handlers: logging.basicConfig(level=logging.INFO) logging.getLogger().handlers[0].setFormatter(formatter) # Redirect stdout and stderr to loggers stdout_logger = logging.getLogger("stdout") stdout_logger.setLevel(logging.INFO) sl = StreamToLogger(stdout_logger, logging.INFO) sys.stdout = sl stderr_logger = logging.getLogger("stderr") stderr_logger.setLevel(logging.ERROR) sl = StreamToLogger(stderr_logger, logging.ERROR) sys.stderr = sl # Get logger logger = logging.getLogger(logger_name) logger.setLevel(logging.INFO) # Add a file handler for all loggers if handler is None: os.makedirs(LOGDIR, exist_ok=True) filename = os.path.join(LOGDIR, logger_filename) handler = logging.handlers.TimedRotatingFileHandler( filename, when='D', utc=True, encoding='UTF-8') handler.setFormatter(formatter) for name, item in logging.root.manager.loggerDict.items(): if isinstance(item, logging.Logger): item.addHandler(handler) return logger class StreamToLogger(object): """ Fake file-like stream object that redirects writes to a logger instance. """ def __init__(self, logger, log_level=logging.INFO): self.terminal = sys.stdout self.logger = logger self.log_level = log_level self.linebuf = '' def __getattr__(self, attr): return getattr(self.terminal, attr) def write(self, buf): temp_linebuf = self.linebuf + buf self.linebuf = '' for line in temp_linebuf.splitlines(True): # From the io.TextIOWrapper docs: # On output, if newline is None, any '\n' characters written # are translated to the system default line separator. # By default sys.stdout.write() expects '\n' newlines and then # translates them so this is still cross platform. if line[-1] == '\n': self.logger.log(self.log_level, line.rstrip()) else: self.linebuf += line def flush(self): if self.linebuf != '': self.logger.log(self.log_level, self.linebuf.rstrip()) self.linebuf = '' def disable_torch_init(): """ Disable the redundant torch default initialization to accelerate model creation. """ import torch setattr(torch.nn.Linear, "reset_parameters", lambda self: None) setattr(torch.nn.LayerNorm, "reset_parameters", lambda self: None) def violates_moderation(text): """ Check whether the text violates OpenAI moderation API. """ url = "https://api.openai.com/v1/moderations" headers = {"Content-Type": "application/json", "Authorization": "Bearer " + os.environ["OPENAI_API_KEY"]} text = text.replace("\n", "") data = "{" + '"input": ' + f'"{text}"' + "}" data = data.encode("utf-8") try: ret = requests.post(url, headers=headers, data=data, timeout=5) flagged = ret.json()["results"][0]["flagged"] except requests.exceptions.RequestException as e: flagged = False except KeyError as e: flagged = False return flagged def pretty_print_semaphore(semaphore): if semaphore is None: return "None" return f"Semaphore(value={semaphore._value}, locked={semaphore.locked()})" ================================================ FILE: playground/data/prompts/complex_reasoning/000_caps.txt ================================================ A man wearing multiple neck ties making a goofy face. A man in a white shirt wearing very many ties. a man with ties on poses for a picture A man wearing multiple ties on his neck. A young man smiles while wearing several ties. tie: [0.574, 0.298, 0.752, 0.704] tie: [0.464, 0.339, 0.639, 0.789] tie: [0.349, 0.363, 0.563, 0.732] tie: [0.259, 0.255, 0.668, 0.805] person: [0.019, 0.065, 0.962, 0.988] person: [0.0, 0.24, 0.214, 1.0] tie: [0.316, 0.778, 0.443, 0.867] tie: [0.386, 0.707, 0.496, 0.801] tie: [0.251, 0.354, 0.402, 0.747] tie: [0.44, 0.318, 0.63, 0.397] tie: [0.566, 0.33, 0.655, 0.543] tie: [0.25, 0.409, 0.359, 0.556] ================================================ FILE: playground/data/prompts/complex_reasoning/000_conv.txt ================================================ Question: What is unusual about this photo? === Answer: In the photo, the man is wearing a total of ten ties around his neck. This is considered unusual because it is not common for someone to wear multiple ties at once. In a typical setting, a person would wear only one tie. The man's goofy facial expression also adds to the unconventional and humorous nature of the image. ================================================ FILE: playground/data/prompts/complex_reasoning/001_caps.txt ================================================ A group of people standing outside of a black vehicle with various luggage. Luggage surrounds a vehicle in an underground parking area People try to fit all of their luggage in an SUV. The sport utility vehicle is parked in the public garage, being packed for a trip Some people with luggage near a van that is transporting it. person: [0.681, 0.242, 0.774, 0.694] person: [0.63, 0.222, 0.686, 0.516] person: [0.444, 0.233, 0.487, 0.34] backpack: [0.384, 0.696, 0.485, 0.914] backpack: [0.755, 0.413, 0.846, 0.692] suitcase: [0.758, 0.413, 0.845, 0.69] suitcase: [0.1, 0.497, 0.173, 0.579] bicycle: [0.282, 0.363, 0.327, 0.442] car: [0.786, 0.25, 0.848, 0.322] car: [0.783, 0.27, 0.827, 0.335] car: [0.86, 0.254, 0.891, 0.3] car: [0.261, 0.101, 0.787, 0.626] ================================================ FILE: playground/data/prompts/complex_reasoning/001_conv.txt ================================================ Question: What challenges do these people face? === Answer: In the image, a group of people is standing outside a black SUV in a parking area, surrounded by various pieces of luggage, including suitcases and backpacks. They are facing the challenge of fitting all their luggage into the black SUV. There are multiple suitcases and backpacks to be packed, which suggests that the group has a significant amount of belongings to accommodate. They might have to strategize and arrange the luggage efficiently to ensure that everything fits properly into the vehicle. Additionally, they need to consider the comfort of the passengers and visibility while driving, so the placement of the luggage must not obstruct the driver's view or make the passengers uncomfortable during the trip. ================================================ FILE: playground/data/prompts/complex_reasoning/002_caps.txt ================================================ There is a movie theater that displays the show times above the doors. A red fire hydrant is deep in the snow. The fire hydrant is in the snow near a recently plowed sidewalk. This city has had a very hard winter with snow. A hotel for dogs in the snow in winter. fire hydrant: [0.326, 0.612, 0.426, 0.72] ================================================ FILE: playground/data/prompts/complex_reasoning/002_conv.txt ================================================ Question: What challenges might this city face? === Answer: The city faces challenges due to the harsh winter conditions and heavy snowfall. In the image, a red fire hydrant is almost buried deep in the snow, which indicates the significant amount of snow the city has experienced. This can lead to various challenges such as difficulties in transportation, increased risk of accidents, and disruptions to daily life. For example, the recently plowed sidewalk near the fire hydrant shows that the city has to constantly clear snow from roads and sidewalks to maintain access and safety for pedestrians and vehicles. Moreover, emergency services, like firefighters, might face challenges accessing crucial equipment, such as fire hydrants, during emergencies due to the snow accumulation. This highlights the importance of effective snow management strategies and preparedness in such cities to minimize the impact of harsh winter conditions on residents and essential services. ================================================ FILE: playground/data/prompts/complex_reasoning/system_message.txt ================================================ You are an AI visual assistant that can analyze a single image. You receive five sentences, each describing the same image you are observing. In addition, specific object locations within the image are given, along with detailed coordinates. These coordinates are in the form of bounding boxes, represented as (x1, y1, x2, y2) with floating numbers ranging from 0 to 1. These values correspond to the top left x, top left y, bottom right x, and bottom right y. The task is to use the provided caption and bounding box information, create a plausible question about the image, and provide the answer in detail. Create complex questions beyond describing the scene. To answer such questions, one should require first understanding the visual content, then based on the background knowledge or reasoning, either explain why the things are happening that way, or provide guides and help to user's request. Make the question challenging by not including the visual content details in the question so that the user needs to reason about that first. Instead of directly mentioning the bounding box coordinates, utilize this data to explain the scene using natural language. Include details like object counts, position of the objects, relative position between the objects. When using the information from the caption and coordinates, directly explain the scene, and do not mention that the information source is the caption or the bounding box. Always answer as if you are directly looking at the image. ================================================ FILE: playground/data/prompts/conversation/000_caps.txt ================================================ There is a movie theater that displays the show times above the doors. A red fire hydrant is deep in the snow. The fire hydrant is in the snow near a recently plowed sidewalk. This city has had a very hard winter with snow. A hotel for dogs in the snow in winter. ================================================ FILE: playground/data/prompts/conversation/000_conv.txt ================================================ Question: What color is the fire hydrant in the image? === Answer: The fire hydrant in the image is red. === Question: Is the fire hydrant fully covered by snow or partially visible? === Answer: The fire hydrant is partially visible, with a significant portion of it covered by the deep snow. === Question: What is the condition of the sidewalk near the fire hydrant? === Answer: The sidewalk near the fire hydrant has been recently plowed, so it is relatively clear of snow compared to the surrounding area. === Question: What does the image suggest about the winter season in the city? === Answer: The image suggests that the winter season in the city has been quite harsh and challenging. The significant snow accumulation seen in the image indicates that the city has experienced heavy snowfall, which can lead to various difficulties and disruptions for its residents. For instance, the deep snow covering the fire hydrant could potentially hinder its accessibility in case of emergencies, which poses safety concerns. The recently plowed sidewalk implies that the city's maintenance crews have been actively working to keep the walkways clear and safe for pedestrians, but the sheer amount of snowfall might make it difficult to keep up with the continuous snow removal efforts. Furthermore, such extreme winter conditions can impact transportation, leading to traffic issues, delays in public transit, and increased risks of accidents due to slippery roads. It can also cause problems for businesses and schools, as people might face challenges commuting to work or attending classes. Additionally, the heavy snow can put extra strain on infrastructure, such as roofs and power lines, increasing the likelihood of structural damage or power outages. In conclusion, the image of the red fire hydrant deep in the snow and the recently plowed sidewalk suggest that the city has faced a particularly severe winter season, with substantial snowfall that has likely caused various challenges and disruptions for its residents and infrastructure. ================================================ FILE: playground/data/prompts/conversation/001_caps.txt ================================================ A man is skiing in the open snow covered hills A skier is making his way into the snow. A skier on the foothills of a huge mountain range. A skier looks at mountains while standing near a trail sign. a single person skiing by an area with a lot of bushes ================================================ FILE: playground/data/prompts/conversation/001_conv.txt ================================================ Question: What is the skier doing? === Answer: The skier is skiing in the snow-covered hills, making his way through the snow and enjoying the beautiful mountain scenery. They are also standing near a trail sign, which indicates their location on the mountain. === Question: Are there any other people or skiers visible in the image? === Answer: No, there is only a single person skiing in the image, and they are surrounded by an area with a lot of bushes. === Question: What kind of skiing is the person doing? Cross-country or downhill? === Answer: Based on what I can see in the photo, it is not possible to definitively determine whether the skier is doing cross-country or downhill skiing. However, given the presence of a trail sign and the fact that they are skiing in the foothills, it is more likely that the skier is engaged in cross-country skiing. Downhill skiing typically takes place on more steep slopes and involves ski lifts, whereas cross-country skiing often occurs on relatively flatter terrain with marked trails. === Question: Can you explain cross-country and downhill skiing a bit more? === Answer: Cross-country skiing and downhill skiing are two distinct types of skiing, each with its own techniques, equipment, and terrain preferences. 1. Cross-Country Skiing: Also known as Nordic skiing, cross-country skiing involves traversing relatively flat terrain or gentle slopes using skis and poles. It is a popular recreational and competitive sport that focuses on endurance, balance, and aerobic fitness. Cross-country skiers use their own locomotion to move across snow-covered terrain, rather than relying on ski lifts or other forms of assistance. There are two main techniques in cross-country skiing: - Classic: This technique involves skiing in parallel tracks, using a forward-and-backward gliding motion while keeping the skis parallel to each other. The skier uses their poles to propel themselves forward. - Skate skiing: This technique is similar to ice skating, where the skier pushes off one ski at an angle and glides on the other. It requires a smooth, groomed surface and is typically faster than the classic technique. Cross-country ski equipment consists of lightweight skis, boots, bindings, and poles. The boots are more flexible than those used in downhill skiing, allowing for better ankle movement and control. 2. Downhill Skiing: Also known as alpine skiing, downhill skiing involves descending slopes at high speeds using skis and poles for balance and control. This sport is more focused on speed, technique, and navigating challenging terrain, including steep slopes, moguls, and even jumps. Downhill skiing can be further categorized into several disciplines, such as slalom, giant slalom, super-G, and downhill racing. Each discipline has its own set of rules, courses, and ski equipment. Downhill ski equipment includes heavier and stiffer skis, boots, bindings, and poles than those used in cross-country skiing. The boots are more rigid to provide better support and control during high-speed descents and sharp turns. In summary, cross-country skiing is an endurance-based sport that involves traveling across flat or gently sloping terrain, while downhill skiing is focused on speed and technique as skiers navigate steeper slopes and challenging terrain. Both sports require specialized equipment and techniques, but they offer different experiences and challenges to participants. ================================================ FILE: playground/data/prompts/conversation/system_message.txt ================================================ You are an AI visual assistant, and you are seeing a single image. What you see are provided with five sentences, describing the same image you are looking at. Answer all questions as you are seeing the image. Design a conversation between you and a person asking about this photo. The answers should be in a tone that a visual AI assistant is seeing the image and answering the question. Ask diverse questions and give corresponding answers. Include questions asking about the visual content of the image, including the object types, counting the objects, object actions, object locations, relative positions between objects, etc. Only include questions that have definite answers: (1) one can see the content in the image that the question asks about and can answer confidently; (2) one can determine confidently from the image that it is not in the image. Do not ask any question that cannot be answered confidently. Also include complex questions that are relevant to the content in the image, for example, asking about background knowledge of the objects in the image, asking to discuss about events happening in the image, etc. Again, do not ask about uncertain details. Provide detailed answers when answering complex questions. For example, give detailed examples or reasoning steps to make the content more convincing and well-organized. You can include multiple paragraphs if necessary. ================================================ FILE: playground/data/prompts/detail_description/000_caps.txt ================================================ A harbor filled with lots of boats next to a building. A bicycle parked in front of several boats at a dock. A red bicycle in front of a line of docked white yachts A bike sits before boats which sit before a long building. A bicycle is a convenient means of land transportation when you live on a boat. bicycle: [0.287, 0.641, 0.507, 0.874] bicycle: [0.566, 0.667, 0.63, 0.731] boat: [0.318, 0.579, 0.575, 0.724] boat: [0.704, 0.607, 0.818, 0.727] boat: [0.818, 0.601, 0.942, 0.744] boat: [0.002, 0.53, 0.243, 0.71] boat: [0.541, 0.611, 0.668, 0.731] person: [0.778, 0.527, 0.797, 0.57] cup: [0.708, 0.733, 0.724, 0.758] boat: [0.236, 0.532, 0.404, 0.64] boat: [0.81, 0.632, 0.836, 0.676] boat: [0.957, 0.526, 1.0, 0.752] ================================================ FILE: playground/data/prompts/detail_description/000_conv.txt ================================================ It is a harbor filled with numerous boats of various sizes docked next to a long building. Among the boats, there are a few white yachts lined up, standing out from the rest. There is a red bicycle prominently parked in front of the line of docked boats, serving as a convenient means of land transportation for those living on the boats. Another bicycle can be seen further back in the scene, near the middle of the harbor. A person is visible near the right side of the harbor, possibly enjoying the view or attending to their boat. Additionally, there is a cup placed on a surface near the middle of the scene. ================================================ FILE: playground/data/prompts/detail_description/001_caps.txt ================================================ A group of people standing outside of a black vehicle with various luggage. Luggage surrounds a vehicle in an underground parking area People try to fit all of their luggage in an SUV. The sport utility vehicle is parked in the public garage, being packed for a trip Some people with luggage near a van that is transporting it. person: [0.681, 0.242, 0.774, 0.694] person: [0.63, 0.222, 0.686, 0.516] person: [0.444, 0.233, 0.487, 0.34] backpack: [0.384, 0.696, 0.485, 0.914] backpack: [0.755, 0.413, 0.846, 0.692] suitcase: [0.758, 0.413, 0.845, 0.69] suitcase: [0.1, 0.497, 0.173, 0.579] bicycle: [0.282, 0.363, 0.327, 0.442] car: [0.786, 0.25, 0.848, 0.322] car: [0.783, 0.27, 0.827, 0.335] car: [0.86, 0.254, 0.891, 0.3] car: [0.261, 0.101, 0.787, 0.626] ================================================ FILE: playground/data/prompts/detail_description/001_conv.txt ================================================ The image is an underground parking area with a black sport utility vehicle (SUV) parked. There are three people in the scene, with one person standing closer to the left side of the vehicle, another person in the middle, and the third person on the right side. They are all working together to pack their luggage into the SUV for a trip. In the parking area, various luggage items are scattered around the vehicle. There are two backpacks, one located near the left rear wheel and the other closer to the right side of the vehicle. Additionally, there are two suitcases, one on the right side of the car and another further away near the center of the parking area. A bicycle can also be seen on the left side of the vehicle. Other cars are parked around the main SUV, with one car positioned behind it and slightly to the left, another behind and slightly to the right, and the third car further behind on the right side. ================================================ FILE: playground/data/prompts/detail_description/002_caps.txt ================================================ A man holds a Wii-mote above his head while another looks on. A guy and his friend are playing Nintendo Wii. A young man is holding a video game remote over his head. two men standing in a room while one plays with a wii mote Some guys standing and playing a video game. couch: [0.697, 0.759, 0.995, 1.0] dining table: [0.426, 0.755, 1.0, 0.987] person: [0.082, 0.252, 0.342, 1.0] person: [0.399, 0.085, 0.742, 0.982] remote: [0.477, 0.135, 0.516, 0.187] sink: [0.016, 0.501, 0.063, 0.52] potted plant: [0.798, 0.384, 0.888, 0.645] refrigerator: [0.305, 0.389, 0.414, 0.547] chair: [0.72, 0.509, 0.858, 0.725] ================================================ FILE: playground/data/prompts/detail_description/002_conv.txt ================================================ The image shows two men standing in a room, engaged in playing a video game on a Nintendo Wii console. One of the men is holding a Wii remote above his head with enthusiasm, while the other man looks on, likely enjoying the friendly competition. The room appears to be a living space with a couch located in the background and a dining table nearby. A potted plant can be seen placed close to the couch, and a chair is situated in the middle of the room. The room also features a kitchen area with a sink and a refrigerator visible in the background. ================================================ FILE: playground/data/prompts/detail_description/system_message.txt ================================================ You are an AI visual assistant that can analyze a single image. You receive five sentences, each describing the same image you are observing. In addition, specific object locations within the image are given, along with detailed coordinates. These coordinates are in the form of bounding boxes, represented as (x1, y1, x2, y2) with floating numbers ranging from 0 to 1. These values correspond to the top left x, top left y, bottom right x, and bottom right y. Using the provided caption and bounding box information, describe the scene in a detailed manner. Instead of directly mentioning the bounding box coordinates, utilize this data to explain the scene using natural language. Include details like object counts, position of the objects, relative position between the objects. When using the information from the caption and coordinates, directly explain the scene, and do not mention that the information source is the caption or the bounding box. Always answer as if you are directly looking at the image. ================================================ FILE: predict.py ================================================ import torch from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN from llava.conversation import conv_templates, SeparatorStyle from llava.model.builder import load_pretrained_model from llava.utils import disable_torch_init from llava.mm_utils import tokenizer_image_token from transformers.generation.streamers import TextIteratorStreamer from PIL import Image import requests from io import BytesIO from cog import BasePredictor, Input, Path, ConcatenateIterator import time import subprocess from threading import Thread import os os.environ["HUGGINGFACE_HUB_CACHE"] = os.getcwd() + "/weights" # url for the weights mirror REPLICATE_WEIGHTS_URL = "https://weights.replicate.delivery/default" # files to download from the weights mirrors weights = [ { "dest": "liuhaotian/llava-v1.5-13b", # git commit hash from huggingface "src": "llava-v1.5-13b/006818fc465ebda4c003c0998674d9141d8d95f8", "files": [ "config.json", "generation_config.json", "pytorch_model-00001-of-00003.bin", "pytorch_model-00002-of-00003.bin", "pytorch_model-00003-of-00003.bin", "pytorch_model.bin.index.json", "special_tokens_map.json", "tokenizer.model", "tokenizer_config.json", ] }, { "dest": "openai/clip-vit-large-patch14-336", "src": "clip-vit-large-patch14-336/ce19dc912ca5cd21c8a653c79e251e808ccabcd1", "files": [ "config.json", "preprocessor_config.json", "pytorch_model.bin" ], } ] def download_json(url: str, dest: Path): res = requests.get(url, allow_redirects=True) if res.status_code == 200 and res.content: with dest.open("wb") as f: f.write(res.content) else: print(f"Failed to download {url}. Status code: {res.status_code}") def download_weights(baseurl: str, basedest: str, files: list[str]): basedest = Path(basedest) start = time.time() print("downloading to: ", basedest) basedest.mkdir(parents=True, exist_ok=True) for f in files: dest = basedest / f url = os.path.join(REPLICATE_WEIGHTS_URL, baseurl, f) if not dest.exists(): print("downloading url: ", url) if dest.suffix == ".json": download_json(url, dest) else: subprocess.check_call(["pget", url, str(dest)], close_fds=False) print("downloading took: ", time.time() - start) class Predictor(BasePredictor): def setup(self) -> None: """Load the model into memory to make running multiple predictions efficient""" for weight in weights: download_weights(weight["src"], weight["dest"], weight["files"]) disable_torch_init() self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model("liuhaotian/llava-v1.5-13b", model_name="llava-v1.5-13b", model_base=None, load_8bit=False, load_4bit=False) def predict( self, image: Path = Input(description="Input image"), prompt: str = Input(description="Prompt to use for text generation"), top_p: float = Input(description="When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens", ge=0.0, le=1.0, default=1.0), temperature: float = Input(description="Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic", default=0.2, ge=0.0), max_tokens: int = Input(description="Maximum number of tokens to generate. A word is generally 2-3 tokens", default=1024, ge=0), ) -> ConcatenateIterator[str]: """Run a single prediction on the model""" conv_mode = "llava_v1" conv = conv_templates[conv_mode].copy() image_data = load_image(str(image)) image_tensor = self.image_processor.preprocess(image_data, return_tensors='pt')['pixel_values'].half().cuda() # loop start # just one turn, always prepend image token inp = DEFAULT_IMAGE_TOKEN + '\n' + prompt conv.append_message(conv.roles[0], inp) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() input_ids = tokenizer_image_token(prompt, self.tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda() stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2 keywords = [stop_str] streamer = TextIteratorStreamer(self.tokenizer, skip_prompt=True, timeout=20.0) with torch.inference_mode(): thread = Thread(target=self.model.generate, kwargs=dict( inputs=input_ids, images=image_tensor, do_sample=True, temperature=temperature, top_p=top_p, max_new_tokens=max_tokens, streamer=streamer, use_cache=True)) thread.start() # workaround: second-to-last token is always " " # but we want to keep it if it's not the second-to-last token prepend_space = False for new_text in streamer: if new_text == " ": prepend_space = True continue if new_text.endswith(stop_str): new_text = new_text[:-len(stop_str)].strip() prepend_space = False elif prepend_space: new_text = " " + new_text prepend_space = False if len(new_text): yield new_text if prepend_space: yield " " thread.join() def load_image(image_file): if image_file.startswith('http') or image_file.startswith('https'): response = requests.get(image_file) image = Image.open(BytesIO(response.content)).convert('RGB') else: image = Image.open(image_file).convert('RGB') return image ================================================ FILE: pyproject.toml ================================================ [build-system] requires = ["setuptools>=61.0"] build-backend = "setuptools.build_meta" [project] name = "llava" version = "1.2.2.post1" description = "Towards GPT-4 like large language and visual assistant." readme = "README.md" requires-python = ">=3.8" classifiers = [ "Programming Language :: Python :: 3", "License :: OSI Approved :: Apache Software License", ] dependencies = [ "torch==2.1.2", "torchvision==0.16.2", "transformers==4.37.2", "tokenizers==0.15.1", "sentencepiece==0.1.99", "shortuuid", "accelerate==0.21.0", "peft", "bitsandbytes", "pydantic", "markdown2[all]", "numpy", "scikit-learn==1.2.2", "gradio==4.16.0", "gradio_client==0.8.1", "requests", "httpx==0.24.0", "uvicorn", "fastapi", "einops==0.6.1", "einops-exts==0.0.4", "timm==0.6.13", ] [project.optional-dependencies] train = ["deepspeed==0.12.6", "ninja", "wandb"] build = ["build", "twine"] [project.urls] "Homepage" = "https://llava-vl.github.io" "Bug Tracker" = "https://github.com/haotian-liu/LLaVA/issues" [tool.setuptools.packages.find] exclude = ["assets*", "benchmark*", "docs", "dist*", "playground*", "scripts*", "tests*"] [tool.wheel] exclude = ["assets*", "benchmark*", "docs", "dist*", "playground*", "scripts*", "tests*"] ================================================ FILE: scripts/convert_gqa_for_eval.py ================================================ import os import json import argparse parser = argparse.ArgumentParser() parser.add_argument("--src", type=str) parser.add_argument("--dst", type=str) args = parser.parse_args() all_answers = [] for line_idx, line in enumerate(open(args.src)): res = json.loads(line) question_id = res['question_id'] text = res['text'].rstrip('.').lower() all_answers.append({"questionId": question_id, "prediction": text}) with open(args.dst, 'w') as f: json.dump(all_answers, f) ================================================ FILE: scripts/convert_mmbench_for_submission.py ================================================ import os import json import argparse import pandas as pd def get_args(): parser = argparse.ArgumentParser() parser.add_argument("--annotation-file", type=str, required=True) parser.add_argument("--result-dir", type=str, required=True) parser.add_argument("--upload-dir", type=str, required=True) parser.add_argument("--experiment", type=str, required=True) return parser.parse_args() if __name__ == "__main__": args = get_args() df = pd.read_table(args.annotation_file) cur_df = df.copy() cur_df = cur_df.drop(columns=['hint', 'category', 'source', 'image', 'comment', 'l2-category']) cur_df.insert(6, 'prediction', None) for pred in open(os.path.join(args.result_dir, f"{args.experiment}.jsonl")): pred = json.loads(pred) cur_df.loc[df['index'] == pred['question_id'], 'prediction'] = pred['text'] cur_df.to_excel(os.path.join(args.upload_dir, f"{args.experiment}.xlsx"), index=False, engine='openpyxl') ================================================ FILE: scripts/convert_mmvet_for_eval.py ================================================ import os import json import argparse parser = argparse.ArgumentParser() parser.add_argument("--src", type=str) parser.add_argument("--dst", type=str) args = parser.parse_args() cur_result = {} for line in open(args.src): data = json.loads(line) qid = data['question_id'] cur_result[f'v1_{qid}'] = data['text'] with open(args.dst, 'w') as f: json.dump(cur_result, f, indent=2) ================================================ FILE: scripts/convert_seed_for_submission.py ================================================ import os import json import argparse def get_args(): parser = argparse.ArgumentParser() parser.add_argument("--annotation-file", type=str) parser.add_argument("--result-file", type=str) parser.add_argument("--result-upload-file", type=str) return parser.parse_args() def eval_single(result_file, eval_only_type=None): results = {} for line in open(result_file): row = json.loads(line) results[row['question_id']] = row type_counts = {} correct_counts = {} for question_data in data['questions']: if eval_only_type is not None and question_data['data_type'] != eval_only_type: continue data_type = question_data['question_type_id'] type_counts[data_type] = type_counts.get(data_type, 0) + 1 try: question_id = int(question_data['question_id']) except: question_id = question_data['question_id'] if question_id not in results: correct_counts[data_type] = correct_counts.get(data_type, 0) continue row = results[question_id] if row['text'] == question_data['answer']: correct_counts[data_type] = correct_counts.get(data_type, 0) + 1 total_count = 0 total_correct = 0 for data_type in sorted(type_counts.keys()): accuracy = correct_counts[data_type] / type_counts[data_type] * 100 if eval_only_type is None: print(f"{ques_type_id_to_name[data_type]}: {accuracy:.2f}%") total_count += type_counts[data_type] total_correct += correct_counts[data_type] total_accuracy = total_correct / total_count * 100 if eval_only_type is None: print(f"Total accuracy: {total_accuracy:.2f}%") else: print(f"{eval_only_type} accuracy: {total_accuracy:.2f}%") return results if __name__ == "__main__": args = get_args() data = json.load(open(args.annotation_file)) ques_type_id_to_name = {id:n for n,id in data['question_type'].items()} results = eval_single(args.result_file) eval_single(args.result_file, eval_only_type='image') eval_single(args.result_file, eval_only_type='video') with open(args.result_upload_file, 'w') as fp: for question in data['questions']: qid = question['question_id'] if qid in results: result = results[qid] else: result = results[int(qid)] fp.write(json.dumps({ 'question_id': qid, 'prediction': result['text'] }) + '\n') ================================================ FILE: scripts/convert_sqa_to_llava.py ================================================ import json import os import fire import re from convert_sqa_to_llava_base_prompt import build_prompt_chatbot def convert_to_llava(base_dir, split, prompt_format="QCM-LEA"): split_indices = json.load(open(os.path.join(base_dir, "pid_splits.json")))[split] problems = json.load(open(os.path.join(base_dir, "problems.json"))) split_problems = build_prompt_chatbot( problems, split_indices, prompt_format, use_caption=False, is_test=False) target_format = [] for prob_id, (input, output) in split_problems.items(): if input.startswith('Question: '): input = input.replace('Question: ', '') if output.startswith('Answer: '): output = output.replace('Answer: ', '') raw_prob_data = problems[prob_id] if raw_prob_data['image'] is None: target_format.append({ "id": prob_id, "conversations": [ {'from': 'human', 'value': f"{input}"}, {'from': 'gpt', 'value': f"{output}"}, ], }) else: target_format.append({ "id": prob_id, "image": os.path.join(prob_id, raw_prob_data['image']), "conversations": [ {'from': 'human', 'value': f"{input}\n"}, {'from': 'gpt', 'value': f"{output}"}, ], }) print(f'Number of samples: {len(target_format)}') with open(os.path.join(base_dir, f"llava_{split}_{prompt_format}.json"), "w") as f: json.dump(target_format, f, indent=2) def convert_to_jsonl(base_dir, split, prompt_format="QCM-LEPA"): split_indices = json.load(open(os.path.join(base_dir, "pid_splits.json")))[split] problems = json.load(open(os.path.join(base_dir, "problems.json"))) split_problems = build_prompt_chatbot( problems, split_indices, prompt_format, use_caption=False, is_test=False) writer = open(os.path.join(base_dir, f"scienceqa_{split}_{prompt_format}.jsonl"), "w") for prob_id, (input, output) in split_problems.items(): if input.startswith('Question: '): input = input.replace('Question: ', '') if output.startswith('Answer: '): output = output.replace('Answer: ', '') raw_prob_data = problems[prob_id] if raw_prob_data['image'] is None: data = { "id": prob_id, "instruction": f"{input}", "output": f"{output}", } else: data = { "id": prob_id, "image": os.path.join(prob_id, raw_prob_data['image']), "instruction": f"{input}\n", "output": f"{output}", } writer.write(json.dumps(data) + '\n') writer.close() def main(task, **kwargs): globals()[task](**kwargs) if __name__ == "__main__": fire.Fire(main) ================================================ FILE: scripts/convert_sqa_to_llava_base_prompt.py ================================================ def get_question_text(problem): question = problem['question'] return question def get_context_text(problem, use_caption): txt_context = problem['hint'] img_context = problem['caption'] if use_caption else "" context = " ".join([txt_context, img_context]).strip() if context == "": context = "N/A" return context def get_choice_text(probelm, options): choices = probelm['choices'] choice_list = [] for i, c in enumerate(choices): choice_list.append("({}) {}".format(options[i], c)) choice_txt = " ".join(choice_list) #print(choice_txt) return choice_txt def get_answer(problem, options): return options[problem['answer']] def get_lecture_text(problem): # \\n: GPT-3 can generate the lecture with more tokens. lecture = problem['lecture'].replace("\n", "\\n") return lecture def get_solution_text(problem): # \\n: GPT-3 can generate the solution with more tokens solution = problem['solution'].replace("\n", "\\n") return solution def create_one_example_chatbot(format, question, context, choice, answer, lecture, solution, test_example=True): input_format, output_format = format.split("-") ## Inputs if input_format == "CQM": input = f"Context: {context}\nQuestion: {question}\nOptions: {choice}\n" elif input_format == "QCM": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\n" # upper bound experiment elif input_format == "QCML": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture}\n" elif input_format == "QCME": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {solution}\n" elif input_format == "QCMLE": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture} {solution}\n" elif input_format == "QCLM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture}\nOptions: {choice}\n" elif input_format == "QCEM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {solution}\nOptions: {choice}\n" elif input_format == "QCLEM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture} {solution}\nOptions: {choice}\n" # Outputs if test_example: output = "Answer:" elif output_format == 'A': output = f"Answer: The answer is {answer}." elif output_format == 'AL': output = f"Answer: The answer is {answer}. BECAUSE: {solution}" elif output_format == 'AE': output = f"Answer: The answer is {answer}. BECAUSE: {lecture}" elif output_format == 'ALE': output = f"Answer: The answer is {answer}. BECAUSE: {lecture} {solution}" elif output_format == 'AEL': output = f"Answer: The answer is {answer}. BECAUSE: {solution} {lecture}" elif output_format == 'LA': output = f"Answer: {lecture} The answer is {answer}." elif output_format == 'EA': output = f"Answer: {solution} The answer is {answer}." elif output_format == 'LEA': output = f"Answer: {lecture} {solution} The answer is {answer}." elif output_format == 'ELA': output = f"Answer: {solution} {lecture} The answer is {answer}." elif output_format == 'LEPA': output = '' if len(lecture.strip()) > 0: output += f"LECTURE: {lecture}\n" if len(solution.strip()) > 0: output += f"SOLUTION: {solution}\n" output += '###\n' output += f"ANSWER: {answer}." input = input.replace(" ", " ").strip() output = output.replace(" ", " ").strip() if input.endswith("BECAUSE:"): input = input.replace("BECAUSE:", "").strip() if output.endswith("BECAUSE:"): output = output.replace("BECAUSE:", "").strip() return input, output def create_one_example(format, question, context, choice, answer, lecture, solution, test_example=True): input_format, output_format = format.split("-") ## Inputs if input_format == "CQM": input = f"Context: {context}\nQuestion: {question}\nOptions: {choice}\n" elif input_format == "QCM": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\n" # upper bound experiment elif input_format == "QCML": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture}\n" elif input_format == "QCME": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {solution}\n" elif input_format == "QCMLE": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture} {solution}\n" elif input_format == "QCLM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture}\nOptions: {choice}\n" elif input_format == "QCEM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {solution}\nOptions: {choice}\n" elif input_format == "QCLEM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture} {solution}\nOptions: {choice}\n" # Outputs if test_example: output = "Answer:" elif output_format == 'A': output = f"Answer: The answer is {answer}." elif output_format == 'AL': output = f"Answer: The answer is {answer}. BECAUSE: {solution}" elif output_format == 'AE': output = f"Answer: The answer is {answer}. BECAUSE: {lecture}" elif output_format == 'ALE': output = f"Answer: The answer is {answer}. BECAUSE: {lecture} {solution}" elif output_format == 'AEL': output = f"Answer: The answer is {answer}. BECAUSE: {solution} {lecture}" elif output_format == 'LA': output = f"Answer: {lecture} The answer is {answer}." elif output_format == 'EA': output = f"Answer: {solution} The answer is {answer}." elif output_format == 'LEA': output = f"Answer: {lecture} {solution} The answer is {answer}." elif output_format == 'ELA': output = f"Answer: {solution} {lecture} The answer is {answer}." text = input + output text = text.replace(" ", " ").strip() if text.endswith("BECAUSE:"): text = text.replace("BECAUSE:", "").strip() return text def create_one_example_gpt4(format, question, context, choice, answer, lecture, solution, test_example=True): input_format, output_format = format.split("-") ## Inputs if input_format == "CQM": input = f"Context: {context}\nQuestion: {question}\nOptions: {choice}\n" elif input_format == "QCM": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\n" # upper bound experiment elif input_format == "QCML": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture}\n" elif input_format == "QCME": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {solution}\n" elif input_format == "QCMLE": input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture} {solution}\n" elif input_format == "QCLM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture}\nOptions: {choice}\n" elif input_format == "QCEM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {solution}\nOptions: {choice}\n" elif input_format == "QCLEM": input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture} {solution}\nOptions: {choice}\n" # Outputs if test_example: output = "Answer:" elif output_format == 'A': output = f"Answer: The answer is {answer}." elif output_format == 'AL': output = f"Answer: The answer is {answer}. BECAUSE: {solution}" elif output_format == 'AE': output = f"Answer: The answer is {answer}. BECAUSE: {lecture}" elif output_format == 'ALE': output = f"Answer: The answer is {answer}. BECAUSE: {lecture} {solution}" elif output_format == 'AEL': output = f"Answer: The answer is {answer}. BECAUSE: {solution} {lecture}" elif output_format == 'LA': output = f"Answer: {lecture} The answer is {answer}." elif output_format == 'EA': output = f"Answer: {solution} The answer is {answer}." elif output_format == 'LEA': output = f"Answer: {lecture} {solution} The answer is {answer}." elif output_format == 'ELA': output = f"Answer: {solution} {lecture} The answer is {answer}." input = input.replace(" ", " ").strip() output = output.replace(" ", " ").strip() if output.endswith("BECAUSE:"): output = output.replace("BECAUSE:", "").strip() user_prompt = {"role": "user", "content": f"Can you explain {input}?"} assistant_prompt = {"role": "assistant", "content": f"{output}"} return user_prompt, assistant_prompt def build_prompt_chatbot(problems, shot_qids, prompt_format, use_caption=False, options=["A", "B", "C", "D", "E"], is_test=False): examples = {} for qid in shot_qids: question = get_question_text(problems[qid]) context = get_context_text(problems[qid], use_caption) choice = get_choice_text(problems[qid], options) answer = get_answer(problems[qid], options) lecture = get_lecture_text(problems[qid]).replace('\\n', '\n') solution = get_solution_text(problems[qid]).replace('\\n', '\n') train_example = create_one_example_chatbot(prompt_format, question, context, choice, answer, lecture, solution, test_example=is_test) examples[qid] = train_example return examples def build_prompt(problems, shot_qids, test_qid, args): examples = [] # n-shot training examples for qid in shot_qids: question = get_question_text(problems[qid]) context = get_context_text(problems[qid], args.use_caption) choice = get_choice_text(problems[qid], args.options) answer = get_answer(problems[qid], args.options) lecture = get_lecture_text(problems[qid]) solution = get_solution_text(problems[qid]) train_example = create_one_example(args.prompt_format, question, context, choice, answer, lecture, solution, test_example=False) examples.append(train_example) # test example question = get_question_text(problems[test_qid]) context = get_context_text(problems[test_qid], args.use_caption) choice = get_choice_text(problems[test_qid], args.options) answer = get_answer(problems[test_qid], args.options) lecture = get_lecture_text(problems[test_qid]) solution = get_solution_text(problems[test_qid]) test_example = create_one_example(args.prompt_format, question, context, choice, answer, lecture, solution, test_example=True) examples.append(test_example) # create the prompt input prompt_input = '\n\n'.join(examples) return prompt_input def build_prompt_gpt4(problems, shot_qids, test_qid, args): prompt_array = [{"role": "system", "content": "You are a helpful assistant."}] # n-shot training examples for qid in shot_qids: question = get_question_text(problems[qid]) context = get_context_text(problems[qid], args.use_caption) choice = get_choice_text(problems[qid], args.options) answer = get_answer(problems[qid], args.options) lecture = get_lecture_text(problems[qid]) solution = get_solution_text(problems[qid]) user_prompt, assistant_prompt = create_one_example_gpt4(args.prompt_format, question, context, choice, answer, lecture, solution, test_example=False) prompt_array.append(user_prompt) prompt_array.append(assistant_prompt) # test example question = get_question_text(problems[test_qid]) context = get_context_text(problems[test_qid], args.use_caption) choice = get_choice_text(problems[test_qid], args.options) answer = get_answer(problems[test_qid], args.options) lecture = get_lecture_text(problems[test_qid]) solution = get_solution_text(problems[test_qid]) user_prompt, assistant_prompt = create_one_example_gpt4(args.prompt_format, question, context, choice, answer, lecture, solution, test_example=True) prompt_array.append(user_prompt) prompt_array.append(assistant_prompt) return prompt_array ================================================ FILE: scripts/convert_vizwiz_for_submission.py ================================================ import os import argparse import json from llava.eval.m4c_evaluator import EvalAIAnswerProcessor def parse_args(): parser = argparse.ArgumentParser() parser.add_argument('--annotation-file', type=str, required=True) parser.add_argument('--result-file', type=str, required=True) parser.add_argument('--result-upload-file', type=str, required=True) return parser.parse_args() if __name__ == '__main__': args = parse_args() os.makedirs(os.path.dirname(args.result_upload_file), exist_ok=True) results = [] error_line = 0 for line_idx, line in enumerate(open(args.result_file)): try: results.append(json.loads(line)) except: error_line += 1 results = {x['question_id']: x['text'] for x in results} test_split = [json.loads(line) for line in open(args.annotation_file)] split_ids = set([x['question_id'] for x in test_split]) print(f'total results: {len(results)}, total split: {len(test_split)}, error_line: {error_line}') all_answers = [] answer_processor = EvalAIAnswerProcessor() for x in test_split: assert x['question_id'] in results all_answers.append({ 'image': x['image'], 'answer': answer_processor(results[x['question_id']]) }) with open(args.result_upload_file, 'w') as f: json.dump(all_answers, f) ================================================ FILE: scripts/convert_vqav2_for_submission.py ================================================ import os import argparse import json from llava.eval.m4c_evaluator import EvalAIAnswerProcessor def parse_args(): parser = argparse.ArgumentParser() parser.add_argument('--dir', type=str, default="./playground/data/eval/vqav2") parser.add_argument('--ckpt', type=str, required=True) parser.add_argument('--split', type=str, required=True) return parser.parse_args() if __name__ == '__main__': args = parse_args() src = os.path.join(args.dir, 'answers', args.split, args.ckpt, 'merge.jsonl') test_split = os.path.join(args.dir, 'llava_vqav2_mscoco_test2015.jsonl') dst = os.path.join(args.dir, 'answers_upload', args.split, f'{args.ckpt}.json') os.makedirs(os.path.dirname(dst), exist_ok=True) results = [] error_line = 0 for line_idx, line in enumerate(open(src)): try: results.append(json.loads(line)) except: error_line += 1 results = {x['question_id']: x['text'] for x in results} test_split = [json.loads(line) for line in open(test_split)] split_ids = set([x['question_id'] for x in test_split]) print(f'total results: {len(results)}, total split: {len(test_split)}, error_line: {error_line}') all_answers = [] answer_processor = EvalAIAnswerProcessor() for x in test_split: if x['question_id'] not in results: all_answers.append({ 'question_id': x['question_id'], 'answer': '' }) else: all_answers.append({ 'question_id': x['question_id'], 'answer': answer_processor(results[x['question_id']]) }) with open(dst, 'w') as f: json.dump(all_answers, open(dst, 'w')) ================================================ FILE: scripts/extract_mm_projector.py ================================================ """ This is just a utility that I use to extract the projector for quantized models. It is NOT necessary at all to train, or run inference/serve demos. Use this script ONLY if you fully understand its implications. """ import os import argparse import torch import json from collections import defaultdict def parse_args(): parser = argparse.ArgumentParser(description='Extract MMProjector weights') parser.add_argument('--model-path', type=str, help='model folder') parser.add_argument('--output', type=str, help='output file') args = parser.parse_args() return args if __name__ == '__main__': args = parse_args() keys_to_match = ['mm_projector'] ckpt_to_key = defaultdict(list) try: model_indices = json.load(open(os.path.join(args.model_path, 'pytorch_model.bin.index.json'))) for k, v in model_indices['weight_map'].items(): if any(key_match in k for key_match in keys_to_match): ckpt_to_key[v].append(k) except FileNotFoundError: # Smaller models or model checkpoints saved by DeepSpeed. v = 'pytorch_model.bin' for k in torch.load(os.path.join(args.model_path, v), map_location='cpu').keys(): if any(key_match in k for key_match in keys_to_match): ckpt_to_key[v].append(k) loaded_weights = {} for ckpt_name, weight_keys in ckpt_to_key.items(): ckpt = torch.load(os.path.join(args.model_path, ckpt_name), map_location='cpu') for k in weight_keys: loaded_weights[k] = ckpt[k] torch.save(loaded_weights, args.output) ================================================ FILE: scripts/finetune.sh ================================================ #!/bin/bash # IMPORTANT: this is the training script for the original LLaVA, NOT FOR LLaVA V1.5! # Uncomment and set the following variables correspondingly to run this script: ################## VICUNA ################## # PROMPT_VERSION=v1 # MODEL_VERSION="vicuna-v1-3-7b" ################## VICUNA ################## ################## LLaMA-2 ################## # PROMPT_VERSION="llava_llama_2" # MODEL_VERSION="llama-2-7b-chat" ################## LLaMA-2 ################## deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero2.json \ --model_name_or_path ./checkpoints/$MODEL_VERSION \ --version $PROMPT_VERSION \ --data_path ./playground/data/llava_instruct_80k.json \ --image_folder /path/to/coco/train2017 \ --vision_tower openai/clip-vit-large-patch14 \ --pretrain_mm_mlp_adapter ./checkpoints/llava-$MODEL_VERSION-pretrain/mm_projector.bin \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 True \ --output_dir ./checkpoints/llava-$MODEL_VERSION-finetune \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/finetune_full_schedule.sh ================================================ #!/bin/bash # IMPORTANT: this is the training script for the original LLaVA, NOT FOR LLaVA V1.5! # Uncomment and set the following variables correspondingly to run this script: ################## VICUNA ################## # PROMPT_VERSION=v1 # MODEL_VERSION="vicuna-v1-3-7b" ################## VICUNA ################## ################## LLaMA-2 ################## # PROMPT_VERSION="llava_llama_2" # MODEL_VERSION="llama-2-7b-chat" ################## LLaMA-2 ################## deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero2.json \ --model_name_or_path ./checkpoints/$MODEL_VERSION \ --version $PROMPT_VERSION \ --data_path ./playground/data/llava_instruct_158k.json \ --image_folder /path/to/coco/train2017 \ --vision_tower openai/clip-vit-large-patch14 \ --pretrain_mm_mlp_adapter ./checkpoints/llava-$MODEL_VERSION-pretrain/mm_projector.bin \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 True \ --output_dir ./checkpoints/llava-$MODEL_VERSION-finetune \ --num_train_epochs 3 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/finetune_lora.sh ================================================ #!/bin/bash # IMPORTANT: this is the training script for the original LLaVA, NOT FOR LLaVA V1.5! # Uncomment and set the following variables correspondingly to run this script: ################## VICUNA ################## # PROMPT_VERSION=v1 # MODEL_VERSION="vicuna-v1-3-7b" ################## VICUNA ################## ################## LLaMA-2 ################## # PROMPT_VERSION="llava_llama_2" # MODEL_VERSION="llama-2-7b-chat" ################## LLaMA-2 ################## deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero2.json \ --lora_enable True \ --model_name_or_path ./checkpoints/$MODEL_VERSION \ --version $PROMPT_VERSION \ --data_path ./playground/data/llava_instruct_80k.json \ --image_folder /path/to/coco/train2017 \ --vision_tower openai/clip-vit-large-patch14 \ --pretrain_mm_mlp_adapter ./checkpoints/llava-$MODEL_VERSION-pretrain/mm_projector.bin \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 True \ --output_dir ./checkpoints/llava-$MODEL_VERSION-finetune_lora \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --lazy_preprocess True \ --dataloader_num_workers 4 \ --report_to wandb ================================================ FILE: scripts/finetune_qlora.sh ================================================ #!/bin/bash # IMPORTANT: this is the training script for the original LLaVA, NOT FOR LLaVA V1.5! # Uncomment and set the following variables correspondingly to run this script: ################## VICUNA ################## # PROMPT_VERSION=v1 # MODEL_VERSION="vicuna-v1-3-7b" ################## VICUNA ################## ################## LLaMA-2 ################## # PROMPT_VERSION="llava_llama_2" # MODEL_VERSION="llama-2-7b-chat" ################## LLaMA-2 ################## deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero2.json \ --lora_enable True \ --bits 4 \ --model_name_or_path ./checkpoints/$MODEL_VERSION \ --version $PROMPT_VERSION \ --data_path ./playground/data/llava_instruct_80k.json \ --image_folder /path/to/coco/train2017 \ --vision_tower openai/clip-vit-large-patch14 \ --pretrain_mm_mlp_adapter ./checkpoints/llava-$MODEL_VERSION-pretrain/mm_projector.bin \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 True \ --output_dir ./checkpoints/llava-$MODEL_VERSION-finetune_lora \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --lazy_preprocess True \ --dataloader_num_workers 4 \ --report_to wandb ================================================ FILE: scripts/finetune_sqa.sh ================================================ #!/bin/bash # IMPORTANT: this is the training script for the original LLaVA, NOT FOR LLaVA V1.5! deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero2.json \ --model_name_or_path lmsys/vicuna-13b-v1.3 \ --version $PROMPT_VERSION \ --data_path /Data/ScienceQA/data/scienceqa/llava_train_QCM-LEA.json \ --image_folder /Data/ScienceQA/data/scienceqa/images/train \ --vision_tower openai/clip-vit-large-patch14 \ --pretrain_mm_mlp_adapter ./checkpoints/huggingface/liuhaotian/llava-pretrain-vicuna-13b-v1.3/mm_projector.bin \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 True \ --output_dir ./checkpoints/llava-vicuna-13b-v1.3-pretrain_lcs558k_plain-ScienceQA_QCM_LEA-12e \ --num_train_epochs 12 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/merge_lora_weights.py ================================================ import argparse from llava.model.builder import load_pretrained_model from llava.mm_utils import get_model_name_from_path def merge_lora(args): model_name = get_model_name_from_path(args.model_path) tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, device_map='cpu') model.save_pretrained(args.save_model_path) tokenizer.save_pretrained(args.save_model_path) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model-path", type=str, required=True) parser.add_argument("--model-base", type=str, required=True) parser.add_argument("--save-model-path", type=str, required=True) args = parser.parse_args() merge_lora(args) ================================================ FILE: scripts/pretrain.sh ================================================ #!/bin/bash # IMPORTANT: this is the training script for the original LLaVA, NOT FOR LLaVA V1.5! # Uncomment and set the following variables correspondingly to run this script: # MODEL_VERSION=vicuna-v1-3-7b # MODEL_VERSION=llama-2-7b-chat ########### DO NOT CHANGE ########### ########### USE THIS FOR BOTH ########### PROMPT_VERSION=plain ########### DO NOT CHANGE ########### deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero2.json \ --model_name_or_path ./checkpoints/$MODEL_VERSION \ --version $PROMPT_VERSION \ --data_path /path/to/pretrain_data.json \ --image_folder /path/to/images \ --vision_tower openai/clip-vit-large-patch14 \ --tune_mm_mlp_adapter True \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 True \ --output_dir ./checkpoints/llava-$MODEL_VERSION-pretrain \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 24000 \ --save_total_limit 1 \ --learning_rate 2e-3 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/pretrain_xformers.sh ================================================ #!/bin/bash # Uncomment and set the following variables correspondingly to run this script: # MODEL_VERSION=vicuna-v1-3-7b # MODEL_VERSION=llama-2-7b-chat ########### DO NOT CHANGE ########### ########### USE THIS FOR BOTH ########### PROMPT_VERSION=plain ########### DO NOT CHANGE ########### deepspeed llava/train/train_xformers.py \ --deepspeed ./scripts/zero2.json \ --model_name_or_path ./checkpoints/$MODEL_VERSION \ --version $PROMPT_VERSION \ --data_path /path/to/pretrain_data.json \ --image_folder /path/to/images \ --vision_tower openai/clip-vit-large-patch14 \ --tune_mm_mlp_adapter True \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 False \ --output_dir ./checkpoints/llava-$MODEL_VERSION-pretrain \ --num_train_epochs 1 \ --per_device_train_batch_size 4 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 4 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 24000 \ --save_total_limit 1 \ --learning_rate 2e-3 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 False \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/sqa_eval_batch.sh ================================================ #!/bin/bash CHUNKS=8 for IDX in {0..7}; do CUDA_VISIBLE_DEVICES=$IDX python -m llava.eval.model_vqa_science \ --model-path liuhaotian/llava-lcs558k-scienceqa-vicuna-13b-v1.3 \ --question-file ~/haotian/datasets/ScienceQA/data/scienceqa/llava_test_QCM-LEA.json \ --image-folder ~/haotian/datasets/ScienceQA/data/scienceqa/images/test \ --answers-file ./test_llava-13b-chunk$CHUNKS_$IDX.jsonl \ --num-chunks $CHUNKS \ --chunk-idx $IDX \ --conv-mode llava_v1 & done ================================================ FILE: scripts/sqa_eval_gather.sh ================================================ #!/bin/bash CHUNKS=8 output_file="test_llava-13b.jsonl" # Clear out the output file if it exists. > "$output_file" # Loop through the indices and concatenate each file. for idx in $(seq 0 $((CHUNKS-1))); do cat "./test_llava-13b-chunk${idx}.jsonl" >> "$output_file" done python llava/eval/eval_science_qa.py \ --base-dir ~/haotian/datasets/ScienceQA/data/scienceqa \ --result-file ./test_llava-13b.jsonl \ --output-file ./test_llava-13b_output.json \ --output-result ./test_llava-13b_result.json ================================================ FILE: scripts/upload_pypi.sh ================================================ #!/bin/bash # Step 0: Clean up rm -rf dist # Step 1: Change the package name to "llava-torch" sed -i 's/name = "llava"/name = "llava-torch"/' pyproject.toml # Step 2: Build the package python -m build # Step 3: Revert the changes in pyproject.toml to the original sed -i 's/name = "llava-torch"/name = "llava"/' pyproject.toml # Step 4: Upload to PyPI python -m twine upload dist/* ================================================ FILE: scripts/v1_5/eval/gqa.sh ================================================ #!/bin/bash gpu_list="${CUDA_VISIBLE_DEVICES:-0}" IFS=',' read -ra GPULIST <<< "$gpu_list" CHUNKS=${#GPULIST[@]} CKPT="llava-v1.5-13b" SPLIT="llava_gqa_testdev_balanced" GQADIR="./playground/data/eval/gqa/data" for IDX in $(seq 0 $((CHUNKS-1))); do CUDA_VISIBLE_DEVICES=${GPULIST[$IDX]} python -m llava.eval.model_vqa_loader \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/gqa/$SPLIT.jsonl \ --image-folder ./playground/data/eval/gqa/data/images \ --answers-file ./playground/data/eval/gqa/answers/$SPLIT/$CKPT/${CHUNKS}_${IDX}.jsonl \ --num-chunks $CHUNKS \ --chunk-idx $IDX \ --temperature 0 \ --conv-mode vicuna_v1 & done wait output_file=./playground/data/eval/gqa/answers/$SPLIT/$CKPT/merge.jsonl # Clear out the output file if it exists. > "$output_file" # Loop through the indices and concatenate each file. for IDX in $(seq 0 $((CHUNKS-1))); do cat ./playground/data/eval/gqa/answers/$SPLIT/$CKPT/${CHUNKS}_${IDX}.jsonl >> "$output_file" done python scripts/convert_gqa_for_eval.py --src $output_file --dst $GQADIR/testdev_balanced_predictions.json cd $GQADIR python eval/eval.py --tier testdev_balanced ================================================ FILE: scripts/v1_5/eval/llavabench.sh ================================================ #!/bin/bash python -m llava.eval.model_vqa \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/llava-bench-in-the-wild/questions.jsonl \ --image-folder ./playground/data/eval/llava-bench-in-the-wild/images \ --answers-file ./playground/data/eval/llava-bench-in-the-wild/answers/llava-v1.5-13b.jsonl \ --temperature 0 \ --conv-mode vicuna_v1 mkdir -p playground/data/eval/llava-bench-in-the-wild/reviews python llava/eval/eval_gpt_review_bench.py \ --question playground/data/eval/llava-bench-in-the-wild/questions.jsonl \ --context playground/data/eval/llava-bench-in-the-wild/context.jsonl \ --rule llava/eval/table/rule.json \ --answer-list \ playground/data/eval/llava-bench-in-the-wild/answers_gpt4.jsonl \ playground/data/eval/llava-bench-in-the-wild/answers/llava-v1.5-13b.jsonl \ --output \ playground/data/eval/llava-bench-in-the-wild/reviews/llava-v1.5-13b.jsonl python llava/eval/summarize_gpt_review.py -f playground/data/eval/llava-bench-in-the-wild/reviews/llava-v1.5-13b.jsonl ================================================ FILE: scripts/v1_5/eval/mmbench.sh ================================================ #!/bin/bash SPLIT="mmbench_dev_20230712" python -m llava.eval.model_vqa_mmbench \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/mmbench/$SPLIT.tsv \ --answers-file ./playground/data/eval/mmbench/answers/$SPLIT/llava-v1.5-13b.jsonl \ --single-pred-prompt \ --temperature 0 \ --conv-mode vicuna_v1 mkdir -p playground/data/eval/mmbench/answers_upload/$SPLIT python scripts/convert_mmbench_for_submission.py \ --annotation-file ./playground/data/eval/mmbench/$SPLIT.tsv \ --result-dir ./playground/data/eval/mmbench/answers/$SPLIT \ --upload-dir ./playground/data/eval/mmbench/answers_upload/$SPLIT \ --experiment llava-v1.5-13b ================================================ FILE: scripts/v1_5/eval/mmbench_cn.sh ================================================ #!/bin/bash SPLIT="mmbench_dev_cn_20231003" python -m llava.eval.model_vqa_mmbench \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/mmbench_cn/$SPLIT.tsv \ --answers-file ./playground/data/eval/mmbench_cn/answers/$SPLIT/llava-v1.5-13b.jsonl \ --lang cn \ --single-pred-prompt \ --temperature 0 \ --conv-mode vicuna_v1 mkdir -p playground/data/eval/mmbench/answers_upload/$SPLIT python scripts/convert_mmbench_for_submission.py \ --annotation-file ./playground/data/eval/mmbench_cn/$SPLIT.tsv \ --result-dir ./playground/data/eval/mmbench_cn/answers/$SPLIT \ --upload-dir ./playground/data/eval/mmbench_cn/answers_upload/$SPLIT \ --experiment llava-v1.5-13b ================================================ FILE: scripts/v1_5/eval/mme.sh ================================================ #!/bin/bash python -m llava.eval.model_vqa_loader \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/MME/llava_mme.jsonl \ --image-folder ./playground/data/eval/MME/MME_Benchmark_release_version \ --answers-file ./playground/data/eval/MME/answers/llava-v1.5-13b.jsonl \ --temperature 0 \ --conv-mode vicuna_v1 cd ./playground/data/eval/MME python convert_answer_to_mme.py --experiment llava-v1.5-13b cd eval_tool python calculation.py --results_dir answers/llava-v1.5-13b ================================================ FILE: scripts/v1_5/eval/mmvet.sh ================================================ #!/bin/bash python -m llava.eval.model_vqa \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/mm-vet/llava-mm-vet.jsonl \ --image-folder ./playground/data/eval/mm-vet/images \ --answers-file ./playground/data/eval/mm-vet/answers/llava-v1.5-13b.jsonl \ --temperature 0 \ --conv-mode vicuna_v1 mkdir -p ./playground/data/eval/mm-vet/results python scripts/convert_mmvet_for_eval.py \ --src ./playground/data/eval/mm-vet/answers/llava-v1.5-13b.jsonl \ --dst ./playground/data/eval/mm-vet/results/llava-v1.5-13b.json ================================================ FILE: scripts/v1_5/eval/pope.sh ================================================ #!/bin/bash python -m llava.eval.model_vqa_loader \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/pope/llava_pope_test.jsonl \ --image-folder ./playground/data/eval/pope/val2014 \ --answers-file ./playground/data/eval/pope/answers/llava-v1.5-13b.jsonl \ --temperature 0 \ --conv-mode vicuna_v1 python llava/eval/eval_pope.py \ --annotation-dir ./playground/data/eval/pope/coco \ --question-file ./playground/data/eval/pope/llava_pope_test.jsonl \ --result-file ./playground/data/eval/pope/answers/llava-v1.5-13b.jsonl ================================================ FILE: scripts/v1_5/eval/qbench.sh ================================================ #!/bin/bash if [ "$1" = "dev" ]; then echo "Evaluating in 'dev' split." elif [ "$1" = "test" ]; then echo "Evaluating in 'test' split." else echo "Unknown split, please choose between 'dev' and 'test'." exit 1 fi python -m llava.eval.model_vqa_qbench \ --model-path liuhaotian/llava-v1.5-13b \ --image-folder ./playground/data/eval/qbench/images_llvisionqa/ \ --questions-file ./playground/data/eval/qbench/llvisionqa_$1.json \ --answers-file ./playground/data/eval/qbench/llvisionqa_$1_answers.jsonl \ --conv-mode llava_v1 \ --lang en ================================================ FILE: scripts/v1_5/eval/qbench_zh.sh ================================================ #!/bin/bash if [ "$1" = "dev" ]; then ZH_SPLIT="验证集" echo "Evaluating in 'dev' split." elif [ "$1" = "test" ]; then ZH_SPLIT="测试集" echo "Evaluating in 'test' split." else echo "Unknown split, please choose between 'dev' and 'test'." exit 1 fi python -m llava.eval.model_vqa_qbench \ --model-path liuhaotian/llava-v1.5-13b \ --image-folder ./playground/data/eval/qbench/images_llvisionqa/ \ --questions-file ./playground/data/eval/qbench/质衡-问答-$ZH_SPLIT.json \ --answers-file ./playground/data/eval/qbench/llvisionqa_zh_$1_answers.jsonl \ --conv-mode llava_v1 \ --lang zh ================================================ FILE: scripts/v1_5/eval/seed.sh ================================================ #!/bin/bash gpu_list="${CUDA_VISIBLE_DEVICES:-0}" IFS=',' read -ra GPULIST <<< "$gpu_list" CHUNKS=${#GPULIST[@]} CKPT="llava-v1.5-13b" for IDX in $(seq 0 $((CHUNKS-1))); do CUDA_VISIBLE_DEVICES=${GPULIST[$IDX]} python -m llava.eval.model_vqa_loader \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/seed_bench/llava-seed-bench.jsonl \ --image-folder ./playground/data/eval/seed_bench \ --answers-file ./playground/data/eval/seed_bench/answers/$CKPT/${CHUNKS}_${IDX}.jsonl \ --num-chunks $CHUNKS \ --chunk-idx $IDX \ --temperature 0 \ --conv-mode vicuna_v1 & done wait output_file=./playground/data/eval/seed_bench/answers/$CKPT/merge.jsonl # Clear out the output file if it exists. > "$output_file" # Loop through the indices and concatenate each file. for IDX in $(seq 0 $((CHUNKS-1))); do cat ./playground/data/eval/seed_bench/answers/$CKPT/${CHUNKS}_${IDX}.jsonl >> "$output_file" done # Evaluate python scripts/convert_seed_for_submission.py \ --annotation-file ./playground/data/eval/seed_bench/SEED-Bench.json \ --result-file $output_file \ --result-upload-file ./playground/data/eval/seed_bench/answers_upload/llava-v1.5-13b.jsonl ================================================ FILE: scripts/v1_5/eval/sqa.sh ================================================ #!/bin/bash python -m llava.eval.model_vqa_science \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/scienceqa/llava_test_CQM-A.json \ --image-folder ./playground/data/eval/scienceqa/images/test \ --answers-file ./playground/data/eval/scienceqa/answers/llava-v1.5-13b.jsonl \ --single-pred-prompt \ --temperature 0 \ --conv-mode vicuna_v1 python llava/eval/eval_science_qa.py \ --base-dir ./playground/data/eval/scienceqa \ --result-file ./playground/data/eval/scienceqa/answers/llava-v1.5-13b.jsonl \ --output-file ./playground/data/eval/scienceqa/answers/llava-v1.5-13b_output.jsonl \ --output-result ./playground/data/eval/scienceqa/answers/llava-v1.5-13b_result.json ================================================ FILE: scripts/v1_5/eval/textvqa.sh ================================================ #!/bin/bash python -m llava.eval.model_vqa_loader \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/textvqa/llava_textvqa_val_v051_ocr.jsonl \ --image-folder ./playground/data/eval/textvqa/train_images \ --answers-file ./playground/data/eval/textvqa/answers/llava-v1.5-13b.jsonl \ --temperature 0 \ --conv-mode vicuna_v1 python -m llava.eval.eval_textvqa \ --annotation-file ./playground/data/eval/textvqa/TextVQA_0.5.1_val.json \ --result-file ./playground/data/eval/textvqa/answers/llava-v1.5-13b.jsonl ================================================ FILE: scripts/v1_5/eval/vizwiz.sh ================================================ #!/bin/bash python -m llava.eval.model_vqa_loader \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/vizwiz/llava_test.jsonl \ --image-folder ./playground/data/eval/vizwiz/test \ --answers-file ./playground/data/eval/vizwiz/answers/llava-v1.5-13b.jsonl \ --temperature 0 \ --conv-mode vicuna_v1 python scripts/convert_vizwiz_for_submission.py \ --annotation-file ./playground/data/eval/vizwiz/llava_test.jsonl \ --result-file ./playground/data/eval/vizwiz/answers/llava-v1.5-13b.jsonl \ --result-upload-file ./playground/data/eval/vizwiz/answers_upload/llava-v1.5-13b.json ================================================ FILE: scripts/v1_5/eval/vqav2.sh ================================================ #!/bin/bash gpu_list="${CUDA_VISIBLE_DEVICES:-0}" IFS=',' read -ra GPULIST <<< "$gpu_list" CHUNKS=${#GPULIST[@]} CKPT="llava-v1.5-13b" SPLIT="llava_vqav2_mscoco_test-dev2015" for IDX in $(seq 0 $((CHUNKS-1))); do CUDA_VISIBLE_DEVICES=${GPULIST[$IDX]} python -m llava.eval.model_vqa_loader \ --model-path liuhaotian/llava-v1.5-13b \ --question-file ./playground/data/eval/vqav2/$SPLIT.jsonl \ --image-folder ./playground/data/eval/vqav2/test2015 \ --answers-file ./playground/data/eval/vqav2/answers/$SPLIT/$CKPT/${CHUNKS}_${IDX}.jsonl \ --num-chunks $CHUNKS \ --chunk-idx $IDX \ --temperature 0 \ --conv-mode vicuna_v1 & done wait output_file=./playground/data/eval/vqav2/answers/$SPLIT/$CKPT/merge.jsonl # Clear out the output file if it exists. > "$output_file" # Loop through the indices and concatenate each file. for IDX in $(seq 0 $((CHUNKS-1))); do cat ./playground/data/eval/vqav2/answers/$SPLIT/$CKPT/${CHUNKS}_${IDX}.jsonl >> "$output_file" done python scripts/convert_vqav2_for_submission.py --split $SPLIT --ckpt $CKPT ================================================ FILE: scripts/v1_5/finetune.sh ================================================ #!/bin/bash deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero3.json \ --model_name_or_path lmsys/vicuna-13b-v1.5 \ --version v1 \ --data_path ./playground/data/llava_v1_5_mix665k.json \ --image_folder ./playground/data \ --vision_tower openai/clip-vit-large-patch14-336 \ --pretrain_mm_mlp_adapter ./checkpoints/llava-v1.5-13b-pretrain/mm_projector.bin \ --mm_projector_type mlp2x_gelu \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --image_aspect_ratio pad \ --group_by_modality_length True \ --bf16 True \ --output_dir ./checkpoints/llava-v1.5-13b \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/v1_5/finetune_lora.sh ================================================ #!/bin/bash deepspeed llava/train/train_mem.py \ --lora_enable True --lora_r 128 --lora_alpha 256 --mm_projector_lr 2e-5 \ --deepspeed ./scripts/zero3.json \ --model_name_or_path lmsys/vicuna-13b-v1.5 \ --version v1 \ --data_path ./playground/data/llava_v1_5_mix665k.json \ --image_folder ./playground/data \ --vision_tower openai/clip-vit-large-patch14-336 \ --pretrain_mm_mlp_adapter ./checkpoints/llava-v1.5-13b-pretrain/mm_projector.bin \ --mm_projector_type mlp2x_gelu \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --image_aspect_ratio pad \ --group_by_modality_length True \ --bf16 True \ --output_dir ./checkpoints/llava-v1.5-13b-lora \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-4 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/v1_5/finetune_task.sh ================================================ #!/bin/bash deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero3.json \ --model_name_or_path liuhaotian/llava-v1.5-13b \ --version v1 \ --data_path ./playground/data/llava_v1_5_mix665k.json \ --image_folder ./playground/data \ --vision_tower openai/clip-vit-large-patch14-336 \ --mm_projector_type mlp2x_gelu \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --image_aspect_ratio pad \ --group_by_modality_length True \ --bf16 True \ --output_dir ./checkpoints/llava-v1.5-13b-task \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/v1_5/finetune_task_lora.sh ================================================ #!/bin/bash deepspeed llava/train/train_mem.py \ --lora_enable True --lora_r 128 --lora_alpha 256 --mm_projector_lr 2e-5 \ --deepspeed ./scripts/zero3.json \ --model_name_or_path liuhaotian/llava-v1.5-13b \ --version v1 \ --data_path ./playground/data/llava_v1_5_mix665k.json \ --image_folder ./playground/data \ --vision_tower openai/clip-vit-large-patch14-336 \ --mm_projector_type mlp2x_gelu \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --image_aspect_ratio pad \ --group_by_modality_length True \ --bf16 True \ --output_dir ./checkpoints/llava-v1.5-13b-task-lora \ --num_train_epochs 1 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50000 \ --save_total_limit 1 \ --learning_rate 2e-4 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb ================================================ FILE: scripts/v1_5/pretrain.sh ================================================ #!/bin/bash deepspeed llava/train/train_mem.py \ --deepspeed ./scripts/zero2.json \ --model_name_or_path lmsys/vicuna-13b-v1.5 \ --version plain \ --data_path ./playground/data/LLaVA-Pretrain/blip_laion_cc_sbu_558k.json \ --image_folder ./playground/data/LLaVA-Pretrain/images \ --vision_tower openai/clip-vit-large-patch14-336 \ --mm_projector_type mlp2x_gelu \ --tune_mm_mlp_adapter True \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --bf16 True \ --output_dir ./checkpoints/llava-v1.5-13b-pretrain \ --num_train_epochs 1 \ --per_device_train_batch_size 32 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 24000 \ --save_total_limit 1 \ --learning_rate 1e-3 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --dataloader_num_workers 4 \ --lazy_preprocess True \ --report_to wandb