[ { "path": ".gitignore", "content": "# Byte-compiled / optimized / DLL files\n__pycache__/\n*.py[cod]\n*$py.class\n\n# C extensions\n*.so\n\n# Distribution / packaging\n.Python\nbuild/\ndevelop-eggs/\ndist/\ndownloads/\neggs/\n.eggs/\nlib/\nlib64/\nparts/\nsdist/\nvar/\nwheels/\nshare/python-wheels/\n*.egg-info/\n.installed.cfg\n*.egg\nMANIFEST\n\n# PyInstaller\n# Usually these files are written by a python script from a template\n# before PyInstaller builds the exe, so as to inject date/other infos into it.\n*.manifest\n*.spec\n\n# Installer logs\npip-log.txt\npip-delete-this-directory.txt\n\n# Unit test / coverage reports\nhtmlcov/\n.tox/\n.nox/\n.coverage\n.coverage.*\n.cache\nnosetests.xml\ncoverage.xml\n*.cover\n*.py,cover\n.hypothesis/\n.pytest_cache/\ncover/\n\n# Translations\n*.mo\n*.pot\n\n# Django stuff:\n*.log\nlocal_settings.py\ndb.sqlite3\ndb.sqlite3-journal\n\n# Flask stuff:\ninstance/\n.webassets-cache\n\n# Scrapy stuff:\n.scrapy\n\n# Sphinx documentation\ndocs/_build/\n\n# PyBuilder\n.pybuilder/\ntarget/\n\n# Jupyter Notebook\n.ipynb_checkpoints\n\n# IPython\nprofile_default/\nipython_config.py\n\n# pyenv\n# For a library or package, you might want to ignore these files since the code is\n# intended to run in multiple environments; otherwise, check them in:\n# .python-version\n\n# pipenv\n# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.\n# However, in case of collaboration, if having platform-specific dependencies or dependencies\n# having no cross-platform support, pipenv may install dependencies that don't work, or not\n# install all needed dependencies.\n#Pipfile.lock\n\n# poetry\n# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.\n# This is especially recommended for binary packages to ensure reproducibility, and is more\n# commonly ignored for libraries.\n# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control\n#poetry.lock\n\n# pdm\n# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.\n#pdm.lock\n# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it\n# in version control.\n# https://pdm.fming.dev/#use-with-ide\n.pdm.toml\n\n# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm\n__pypackages__/\n\n# Celery stuff\ncelerybeat-schedule\ncelerybeat.pid\n\n# SageMath parsed files\n*.sage.py\n\n# Environments\n.env\n.venv\nenv/\nvenv/\nENV/\nenv.bak/\nvenv.bak/\n\n# Spyder project settings\n.spyderproject\n.spyproject\n\n# Rope project settings\n.ropeproject\n\n# mkdocs documentation\n/site\n\n# mypy\n.mypy_cache/\n.dmypy.json\ndmypy.json\n\n# Pyre type checker\n.pyre/\n\n# pytype static type analyzer\n.pytype/\n\n# Cython debug symbols\ncython_debug/\n\n# PyCharm\n# JetBrains specific template is maintained in a separate JetBrains.gitignore that can\n# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore\n# and can be added to the global gitignore or merged into this file. For a more nuclear\n# option (not recommended) you can uncomment the following to ignore the entire idea folder.\n#.idea/\n" }, { "path": "LICENSE", "content": " Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n\n TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n 1. Definitions.\n\n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n\n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n\n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n\n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n\n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n\n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n\n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n\n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n\n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n\n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n\n 2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n\n 3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n\n 4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n\n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n\n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n\n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n\n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n\n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n\n 5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n\n 6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n\n 7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n\n 8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n\n 9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n\n END OF TERMS AND CONDITIONS\n\n APPENDIX: How to apply the Apache License to your work.\n\n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n\n Copyright [yyyy] [name of copyright owner]\n\n Licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.\n" }, { "path": "README.md", "content": "# OpenLLaMA: An Open Reproduction of LLaMA\n\n**TL;DR**: we are releasing our public preview of OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA. We are releasing a series of 3B, 7B and 13B models trained on different data mixtures. Our model weights can serve as the drop in replacement of LLaMA in existing implementations.\n\nIn this repo, we present a permissively licensed open source reproduction of Meta AI's [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) large language model. We are releasing a series of 3B, 7B and 13B models trained on 1T tokens. We provide PyTorch and JAX weights of pre-trained OpenLLaMA models, as well as evaluation results and comparison against the original LLaMA models. The v2 model is better than the old v1 model trained on a different data mixture.\n\n#### PyTorch weights for Hugging Face transformers:\n- **v2 Models**\n - [OpenLLaMA 3Bv2](https://huggingface.co/openlm-research/open_llama_3b_v2)\n - [OpenLLaMA 7Bv2](https://huggingface.co/openlm-research/open_llama_7b_v2)\n- **v1 Models**\n - [OpenLLaMA 3B](https://huggingface.co/openlm-research/open_llama_3b)\n - [OpenLLaMA 7B](https://huggingface.co/openlm-research/open_llama_7b)\n - [OpenLLaMA 13B](https://huggingface.co/openlm-research/open_llama_13b)\n\n#### JAX weights for [EasyLM](https://github.com/young-geng/EasyLM):\n- **v2 Models**\n - [OpenLLaMA 3Bv2 for EasyLM](https://huggingface.co/openlm-research/open_llama_3b_v2_easylm)\n - [OpenLLaMA 7Bv2 for EasyLM](https://huggingface.co/openlm-research/open_llama_7b_v2_easylm)\n- **v1 Models**\n - [OpenLLaMA 3B for EasyLM](https://huggingface.co/openlm-research/open_llama_3b_easylm)\n - [OpenLLaMA 7B for EasyLM](https://huggingface.co/openlm-research/open_llama_7b_easylm)\n - [OpenLLaMA 13B for EasyLM](https://huggingface.co/openlm-research/open_llama_13b_easylm)\n[](https://huggingface.co/openlm-research/open_llama_3b_600bt_preview_easylm)\n\n\n## Updates\n\n#### 07/15/2023\nWe are releasing the OpenLLaMA 3Bv3 model, which is a 3B model trained for 1T tokens on the same dataset mixture as the 7Bv2 model.\n\n#### 07/07/2023\nWe are happy to release an OpenLLaMA 7Bv2 model, which is trained on a mixture of [Falcon refined-web dataset](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), mixed with the [starcoder dataset](https://huggingface.co/datasets/bigcode/starcoderdata), and the wikipedia, arxiv and books and stackexchange from [RedPajama](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T).\n\n#### 06/15/2023\nWe are happy to release our final 1T token version of OpenLLaMA 13B. We’ve updated the evaluation results. For current version of OpenLLaMA models, our tokenizer is trained to merge multiple empty spaces into one before tokenization, similar to T5 tokenizer. Because of this, our tokenizer will not work with code generation tasks (e.g. HumanEval) since code involves many empty spaces. For code related tasks, please use the v2 models.\n\n#### 06/07/2023\nWe are happy to release our final 1T token version of OpenLLaMA 3B and 7B. We’ve updated the evaluation results. We are also happy to release a 600B token preview of the 13B model, trained in collaboration with [Stability AI](https://stability.ai/).\n\n#### 05/22/2023\nWe are happy to release our 700B token checkpoint for the OpenLLaMA 7B model and 600B token checkpoint for the 3B model. We’ve also updated the evaluation results. We expect the full 1T token training run to finish at the end of this week.\n\n#### 05/15/2023\nAfter receiving feedback from the community, we discovered that the tokenizer of our previous checkpoint release was configured incorrectly so that new lines are not preserved. To fix this problem, we have retrained our tokenizer and restarted the model training. We’ve also observed lower training loss with this new tokenizer.\n\n\n\n## Weights Release, License and Usage\n\nWe release the weights in two formats: an EasyLM format to be use with our [EasyLM framework](https://github.com/young-geng/EasyLM), and a PyTorch format to be used with the [Hugging Face transformers](https://huggingface.co/docs/transformers/index) library. Both our training framework EasyLM and the checkpoint weights are licensed permissively under the Apache 2.0 license.\n\n### Loading the Weights with Hugging Face Transformers\nPreview checkpoints can be directly loaded from Hugging Face Hub. **Please note that it is advised to avoid using the Hugging Face fast tokenizer for now, as we’ve observed that** [**the auto-converted fast tokenizer sometimes gives incorrect tokenizations**](https://github.com/huggingface/transformers/issues/24233)**.** This can be achieved by directly using the `LlamaTokenizer` class, or passing in the `use_fast=False` option for the `AutoTokenizer` class. See the following example for usage.\n\n```python\nimport torch\nfrom transformers import LlamaTokenizer, LlamaForCausalLM\n\n## v2 models\nmodel_path = 'openlm-research/open_llama_3b_v2'\n# model_path = 'openlm-research/open_llama_7b_v2'\n\n## v1 models\n# model_path = 'openlm-research/open_llama_3b'\n# model_path = 'openlm-research/open_llama_7b'\n# model_path = 'openlm-research/open_llama_13b'\n\ntokenizer = LlamaTokenizer.from_pretrained(model_path)\nmodel = LlamaForCausalLM.from_pretrained(\n model_path, torch_dtype=torch.float16, device_map='auto',\n)\n\nprompt = 'Q: What is the largest animal?\\nA:'\ninput_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n\ngeneration_output = model.generate(\n input_ids=input_ids, max_new_tokens=32\n)\nprint(tokenizer.decode(generation_output[0]))\n```\n\nFor more advanced usage, please follow the [transformers LLaMA documentation](https://huggingface.co/docs/transformers/main/model_doc/llama).\n\n### Evaluating with LM-Eval-Harness\nThe model can be evaluated with [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness). However, due to the aforementioned tokenizer issue, we need to avoid using the fast tokenizer to obtain the correct results. This can be achieved by passing in `use_fast=False` to [this part of lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness/blob/4b701e228768052cfae9043dca13e82052ca5eea/lm_eval/models/huggingface.py#LL313C9-L316C10), as shown in the example below:\n\n```python\ntokenizer = self.AUTO_TOKENIZER_CLASS.from_pretrained(\n pretrained if tokenizer is None else tokenizer,\n revision=revision + (\"/\" + subfolder if subfolder is not None else \"\"),\n use_fast=False\n)\n```\n\n### Loading the Weights with EasyLM\nFor using the weights in our EasyLM framework, please refer to the [LLaMA documentation of EasyLM](https://github.com/young-geng/EasyLM/blob/main/docs/llama.md). Note that unlike the original LLaMA model, our OpenLLaMA tokenizer and weights are trained completely from scratch so it is no longer needed to obtain the original LLaMA tokenizer and weights.\n\n\n\n## Dataset and Training\n\nThe v1 models are trained on the [RedPajama dataset](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T). The v2 models are trained on a mixture of the [Falcon refined-web dataset](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), the [StarCoder dataset](https://huggingface.co/datasets/bigcode/starcoderdata) and the wikipedia, arxiv, book and stackexchange part of the [RedPajama dataset](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T). We follow the exactly same preprocessing steps and training hyperparameters as the original LLaMA paper, including model architecture, context length, training steps, learning rate schedule, and optimizer. The only difference between our setting and the original one is the dataset used: OpenLLaMA employs open datasets rather than the one utilized by the original LLaMA.\n\nWe train the models on cloud TPU-v4s using [EasyLM](https://github.com/young-geng/EasyLM), a JAX based training pipeline we developed for training and fine-tuning large language models. We employ a combination of normal data parallelism and fully sharded data parallelism [](https://engineering.fb.com/2021/07/15/open-source/fsdp/)(also know as ZeRO stage 3) to balance the training throughput and memory usage. Overall we reach a throughput of over 2200 tokens / second / TPU-v4 chip for our 7B model. The training loss can be seen in the figure below.\n\n![](media/loss.png)\n\n## Evaluation\n\nWe evaluated OpenLLaMA on a wide range of tasks using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). The LLaMA results are generated by running the original LLaMA model on the same evaluation metrics. We note that our results for the LLaMA model differ slightly from the original LLaMA paper, which we believe is a result of different evaluation protocols. Similar differences have been reported in [this issue of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/issues/443). Additionally, we present the results of GPT-J, a 6B parameter model trained on the [Pile](https://pile.eleuther.ai/) dataset by [EleutherAI](https://www.eleuther.ai/).\n\nThe original LLaMA model was trained for 1 trillion tokens and GPT-J was trained for 500 billion tokens. We present the results in the table below. OpenLLaMA exhibits comparable performance to the original LLaMA and GPT-J across a majority of tasks, and outperforms them in some tasks.\n\n\n| **Task/Metric** | GPT-J 6B | LLaMA 7B | LLaMA 13B | OpenLLaMA 3Bv2 | OpenLLaMA 7Bv2 | OpenLLaMA 3B | OpenLLaMA 7B | OpenLLaMA 13B |\n| ---------------------- | -------- | -------- | --------- | -------------- | -------------- | ------------ | ------------ | ------------- |\n| anli_r1/acc | 0.32 | 0.35 | 0.35 | 0.33 | 0.34 | 0.33 | 0.33 | 0.33 |\n| anli_r2/acc | 0.34 | 0.34 | 0.36 | 0.36 | 0.35 | 0.32 | 0.36 | 0.33 |\n| anli_r3/acc | 0.35 | 0.37 | 0.39 | 0.38 | 0.39 | 0.35 | 0.38 | 0.40 |\n| arc_challenge/acc | 0.34 | 0.39 | 0.44 | 0.34 | 0.39 | 0.34 | 0.37 | 0.41 |\n| arc_challenge/acc_norm | 0.37 | 0.41 | 0.44 | 0.36 | 0.41 | 0.37 | 0.38 | 0.44 |\n| arc_easy/acc | 0.67 | 0.68 | 0.75 | 0.68 | 0.73 | 0.69 | 0.72 | 0.75 |\n| arc_easy/acc_norm | 0.62 | 0.52 | 0.59 | 0.63 | 0.70 | 0.65 | 0.68 | 0.70 |\n| boolq/acc | 0.66 | 0.75 | 0.71 | 0.66 | 0.72 | 0.68 | 0.71 | 0.75 |\n| hellaswag/acc | 0.50 | 0.56 | 0.59 | 0.52 | 0.56 | 0.49 | 0.53 | 0.56 |\n| hellaswag/acc_norm | 0.66 | 0.73 | 0.76 | 0.70 | 0.75 | 0.67 | 0.72 | 0.76 |\n| openbookqa/acc | 0.29 | 0.29 | 0.31 | 0.26 | 0.30 | 0.27 | 0.30 | 0.31 |\n| openbookqa/acc_norm | 0.38 | 0.41 | 0.42 | 0.38 | 0.41 | 0.40 | 0.40 | 0.43 |\n| piqa/acc | 0.75 | 0.78 | 0.79 | 0.77 | 0.79 | 0.75 | 0.76 | 0.77 |\n| piqa/acc_norm | 0.76 | 0.78 | 0.79 | 0.78 | 0.80 | 0.76 | 0.77 | 0.79 |\n| record/em | 0.88 | 0.91 | 0.92 | 0.87 | 0.89 | 0.88 | 0.89 | 0.91 |\n| record/f1 | 0.89 | 0.91 | 0.92 | 0.88 | 0.89 | 0.89 | 0.90 | 0.91 |\n| rte/acc | 0.54 | 0.56 | 0.69 | 0.55 | 0.57 | 0.58 | 0.60 | 0.64 |\n| truthfulqa_mc/mc1 | 0.20 | 0.21 | 0.25 | 0.22 | 0.23 | 0.22 | 0.23 | 0.25 |\n| truthfulqa_mc/mc2 | 0.36 | 0.34 | 0.40 | 0.35 | 0.35 | 0.35 | 0.35 | 0.38 |\n| wic/acc | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.48 | 0.51 | 0.47 |\n| winogrande/acc | 0.64 | 0.68 | 0.70 | 0.63 | 0.66 | 0.62 | 0.67 | 0.70 |\n| Average | 0.52 | 0.55 | 0.57 | 0.53 | 0.56 | 0.53 | 0.55 | 0.57 |\n\n\nWe removed the task CB and WSC from our benchmark, as our model performs suspiciously high on these two tasks. We hypothesize that there could be a benchmark data contamination in the training set.\n\n\n## Contact\n\nWe would love to get feedback from the community. If you have any questions, please open an issue or contact us.\n\nOpenLLaMA is developed by:\n[Xinyang Geng](https://young-geng.xyz/)* and [Hao Liu](https://www.haoliu.site/)* from Berkeley AI Research.\n*Equal Contribution\n\n\n\n## Acknowledgment\n\nWe thank the [Google TPU Research Cloud](https://sites.research.google/trc/about/) program for providing part of the computation resources. We’d like to specially thank Jonathan Caton from TPU Research Cloud for helping us organizing compute resources, Rafi Witten from the Google Cloud team and James Bradbury from the Google JAX team for helping us optimizing our training throughput. We’d also want to thank Charlie Snell, Gautier Izacard, Eric Wallace, Lianmin Zheng and our user community for the discussions and feedback.\n\nThe OpenLLaMA 13B v1 model is trained in collaboration with [Stability AI](https://stability.ai/), and we thank Stability AI for providing the computation resources. We’d like to especially thank David Ha and Shivanshu Purohit for the coordinating the logistics and providing engineering support.\n\n\n## Reference\n\nIf you found OpenLLaMA useful in your research or applications, please cite using the following BibTeX:\n```\n@software{openlm2023openllama,\n author = {Geng, Xinyang and Liu, Hao},\n title = {OpenLLaMA: An Open Reproduction of LLaMA},\n month = May,\n year = 2023,\n url = {https://github.com/openlm-research/open_llama}\n}\n```\n```\n@software{together2023redpajama,\n author = {Together Computer},\n title = {RedPajama-Data: An Open Source Recipe to Reproduce LLaMA training dataset},\n month = April,\n year = 2023,\n url = {https://github.com/togethercomputer/RedPajama-Data}\n}\n```\n```\n@article{touvron2023llama,\n title={Llama: Open and efficient foundation language models},\n author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\\'e}e and Rozi{\\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and others},\n journal={arXiv preprint arXiv:2302.13971},\n year={2023}\n}\n```\n\n\n\n\n\n" } ]