Full Code of soulteary/docker-llama2-chat for AI

Repository: soulteary/docker-llama2-chat
Branch: main
Commit: 4bc43122cfe4
Files: 28
Total size: 62.6 KB

Directory structure:
gitextract_5db6cfvo/

├── .gitignore
├── LICENSE
├── README.md
├── README_EN.md
├── docker/
│   ├── Dockerfile.13b
│   ├── Dockerfile.7b
│   ├── Dockerfile.7b-cn
│   ├── Dockerfile.7b-cn-4bit
│   └── Dockerfile.base
├── llama.cpp/
│   ├── Dockerfile.converter
│   └── Dockerfile.runtime
├── llama2-13b/
│   ├── app.py
│   └── model.py
├── llama2-7b/
│   ├── app.py
│   └── model.py
├── llama2-7b-cn/
│   ├── app.py
│   └── model.py
├── llama2-7b-cn-4bit/
│   ├── app.py
│   ├── model.py
│   └── quantization_4bit.py
└── scripts/
    ├── make-13b.sh
    ├── make-7b-cn-4bit.sh
    ├── make-7b-cn.sh
    ├── make-7b.sh
    ├── run-13b.sh
    ├── run-7b-cn-4bit.sh
    ├── run-7b-cn.sh
    └── run-7b.sh

================================================
FILE CONTENTS
================================================

================================================
FILE: .gitignore
================================================
.DS_Store


================================================
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
================================================
# Docker LLaMA2 Chat / 羊驼二代

<p style="text-align: center;">
  <a href="README.md"  target="_blank">中文文档</a> | <a href="README_EN.md">ENGLISH</a>
</p>

[![](https://img.shields.io/badge/LLaMA2-Official_7B_/_13B-blue)](https://huggingface.co/meta-llama) [![](https://img.shields.io/badge/LLaMA2-Chinese_7B-blue)](https://huggingface.co/soulteary/Chinese-Llama-2-7b-4bit) [![](https://img.shields.io/badge/LLaMA2-Chinese_GGMLQ4-blue)](https://huggingface.co/soulteary/Chinese-Llama-2-7b-ggml-q4) [![](https://img.shields.io/badge/License-Apache_v2-blue)](https://github.com/soulteary/docker-llama2-chat/blob/main/LICENSE)

<img src=".github/llama2.jpg" width="40%">

三步上手 LLaMA2，一起玩！相关博客教程已更新，**同样欢迎“一键三连”** 🌟🌟🌟。

> 使用 Docker 快速上手，本地部署 7B 或 13B 官方模型，或者 7B 中文模型。

### 博客教程

| 类型 | 显存需求 | 特点 | 教程地址 | 教程时间 |
| --- | --- | --- | --- | --- |
| 官方版（英文） | 8~14GB | 原汁原味 | [使用 Docker 快速上手官方版 LLaMA2 开源大模型](https://soulteary.com/2023/07/21/use-docker-to-quickly-get-started-with-the-official-version-of-llama2-open-source-large-model.html) | 2023.07.21 |
| LinkSoul 中文版（双语）| 8~14GB | 支持中文 | [使用 Docker 快速上手中文版 LLaMA2 开源大模型](https://soulteary.com/2023/07/21/use-docker-to-quickly-get-started-with-the-chinese-version-of-llama2-open-source-large-model.html) | 2023.07.21 |
| Transformers 量化（中文/官方） | 5GB | 加速推理、节约显存 | [使用 Transformers 量化 Meta AI LLaMA2 中文版大模型](https://soulteary.com/2023/07/22/quantizing-meta-ai-llama2-chinese-version-large-models-using-transformers.html) | 2023.07.22 |
| GGML (Llama.cpp) 量化 （中文/官方）| 可以不需要显存 | CPU 推理 | [构建能够使用 CPU 运行的 MetaAI LLaMA2 中文大模型](https://soulteary.com/2023/07/23/build-llama2-chinese-large-model-that-can-run-on-cpu.html) | 2023.07.23 |


你可以参考项目代码，举一反三，把模型跑起来，接入到你想玩的地方，包括并不局限于支持 LLaMA 1代的各种开源软件中。

## 预览图

![](.github/preview.png)

![](.github/llama2-cn-4bit.jpg)

![](.github/clip.gif)

## 使用方法

1. 一条命令，从项目中构建官方版（7B或13B）模型镜像，或中文版镜像（7B或INT4量化版）：

```bash
# 7B
bash scripts/make-7b.sh

# 或 13B
bash scripts/make-13b.sh

# 或 7B Chinese
bash scripts/make-7b-cn.sh

# 或 7B Chinese 4bit
bash scripts/make-7b-cn-4bit.sh
```

2. 选择适合你的命令，从 HuggingFace 下载 LLaMA2 或中文模型：

```bash
# MetaAI LLaMA2 Models (10~14GB vRAM)
git clone https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
git clone https://huggingface.co/meta-llama/Llama-2-13b-chat-hf

mkdir meta-llama
mv Llama-2-7b-chat-hf meta-llama/
mv Llama-2-13b-chat-hf meta-llama/

# 或 Chinese LLaMA2 (10~14GB vRAM)
git clone https://huggingface.co/LinkSoul/Chinese-Llama-2-7b

mkdir LinkSoul
mv Chinese-Llama-2-7b LinkSoul/

# 或 Chinese LLaMA2 4BIT (5GB vRAM)
git clone https://huggingface.co/soulteary/Chinese-Llama-2-7b-4bit

mkdir soulteary
mv Chinese-Llama-2-7b-4bit soulteary/
```

将下载好的模型，保持在一个正确的目录结构中。

```bash
tree -L 2 meta-llama
soulteary
└── ...
LinkSoul
└── ...
meta-llama
├── Llama-2-13b-chat-hf
│   ├── added_tokens.json
│   ├── config.json
│   ├── generation_config.json
│   ├── LICENSE.txt
│   ├── model-00001-of-00003.safetensors
│   ├── model-00002-of-00003.safetensors
│   ├── model-00003-of-00003.safetensors
│   ├── model.safetensors.index.json
│   ├── pytorch_model-00001-of-00003.bin
│   ├── pytorch_model-00002-of-00003.bin
│   ├── pytorch_model-00003-of-00003.bin
│   ├── pytorch_model.bin.index.json
│   ├── README.md
│   ├── Responsible-Use-Guide.pdf
│   ├── special_tokens_map.json
│   ├── tokenizer_config.json
│   ├── tokenizer.model
│   └── USE_POLICY.md
└── Llama-2-7b-chat-hf
    ├── added_tokens.json
    ├── config.json
    ├── generation_config.json
    ├── LICENSE.txt
    ├── model-00001-of-00002.safetensors
    ├── model-00002-of-00002.safetensors
    ├── model.safetensors.index.json
    ├── models--meta-llama--Llama-2-7b-chat-hf
    ├── pytorch_model-00001-of-00003.bin
    ├── pytorch_model-00002-of-00003.bin
    ├── pytorch_model-00003-of-00003.bin
    ├── pytorch_model.bin.index.json
    ├── README.md
    ├── special_tokens_map.json
    ├── tokenizer_config.json
    ├── tokenizer.json
    ├── tokenizer.model
    └── USE_POLICY.md
```

3. 选择使用下面的适合你的命令，一键运行 LLaMA2 模型应用：

```bash
# 7B
bash scripts/run-7b.sh
# 或 13B
bash scripts/run-13b.sh
# 或 Chinese 7B
bash scripts/run-7b-cn.sh
# 或 Chinese 7B 4BIT
bash scripts/run-7b-cn-4bit.sh
```

模型运行之后，在浏览器中访问 `http://localhost7860` 或者 `http://你的IP地址:7860` 就可以开始玩了。

## 相关项目

- MetaAI LLaMA2: https://ai.meta.com/llama/ ❤️
- Meta LLaMA2 7B Chat: https://huggingface.co/meta-llama/Llama-2-7b-chat
- Meta LLaMA2 13B Chat: https://huggingface.co/meta-llama/Llama-2-13b-chat
- Chinese LLaMA2 7B: https://huggingface.co/LinkSoul/Chinese-Llama-2-7b ❤️
- Chinese LLaMA2 7B GGML q4: https://huggingface.co/soulteary/Chinese-Llama-2-7b-ggml-q4
- LLaMA2 GGML Converter: https://hub.docker.com/r/soulteary/llama2


================================================
FILE: README_EN.md
================================================
# Docker LLaMA2 Chat / 羊驼二代

<p style="text-align: center;">
  <a href="README_EN.md">ENGLISH</a> | <a href="README.md"  target="_blank">中文文档</a>
</p>

[![](https://img.shields.io/badge/LLaMA2-Official_7B_/_13B-blue)](https://huggingface.co/meta-llama) [![](https://img.shields.io/badge/LLaMA2-Chinese_7B-blue)](https://huggingface.co/soulteary/Chinese-Llama-2-7b-4bit) [![](https://img.shields.io/badge/LLaMA2-Chinese_GGMLQ4-blue)](https://huggingface.co/soulteary/Chinese-Llama-2-7b-ggml-q4) [![](https://img.shields.io/badge/License-Apache_v2-blue)](https://github.com/soulteary/docker-llama2-chat/blob/main/LICENSE)

<img src=".github/llama2.jpg" width="40%">

Play! Together! **ONLY 3 STEPS!**

Get started quickly, locally using the 7B or 13B models, using Docker.

- Meta Llama2, tested by 4090, and costs 8~14GB vRAM.
- Chinese Llama2 quantified, tested by 4090, and costs 5GB vRAM.
- Use GGML(LLaMA.cpp), just use CPU play it.

## Preview

![](.github/preview.png)

![](.github/llama2-cn-4bit.jpg)

![](.github/clip.gif)


## Blogs

- [Use Docker to quickly get started with the official version of Llama2 Open-source Large Model](https://soulteary.com/2023/07/21/use-docker-to-quickly-get-started-with-the-official-version-of-llama2-open-source-large-model.html)
- [Use Docker to quickly get started with the chinese version of Llama2 Open-source Large Model](https://soulteary.com/2023/07/21/use-docker-to-quickly-get-started-with-the-chinese-version-of-llama2-open-source-large-model.html)
- [Quantizing MetaAI Llama2 chinese version large models using Transformers](https://soulteary.com/2023/07/22/quantizing-meta-ai-llama2-chinese-version-large-models-using-transformers.html)
- [Build Llama2 chinese large model that can run on CPU](https://soulteary.com/2023/07/23/build-llama2-chinese-large-model-that-can-run-on-cpu.html)


## Usage

1. Build LLaMA2 Docker image for 7B / 13B (official), 7B or 7B INT4 (chinese):

```bash
# 7B
bash scripts/make-7b.sh

# OR 13B
bash scripts/make-13b.sh

# OR 7B Chinese
bash scripts/make-7b-cn.sh

# OR 7B Chinese 4bit
bash scripts/make-7b-cn-4bit.sh
```

2. Download LLaMA2 Models from HuggingFace, or chinese models.

```bash
# MetaAI LLaMA2 Models (10~14GB vRAM)
git clone https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
git clone https://huggingface.co/meta-llama/Llama-2-13b-chat-hf

mkdir meta-llama
mv Llama-2-7b-chat-hf meta-llama/
mv Llama-2-13b-chat-hf meta-llama/

# OR Chinese LLaMA2 (10~14GB vRAM)
git clone https://huggingface.co/LinkSoul/Chinese-Llama-2-7b

mkdir LinkSoul
mv Chinese-Llama-2-7b LinkSoul/

# OR Chinese LLaMA2 4BIT (5GB vRAM)
git clone https://huggingface.co/soulteary/Chinese-Llama-2-7b-4bit

mkdir soulteary
mv Chinese-Llama-2-7b-4bit soulteary/
```

keep the correct directory structure.

```bash
tree -L 2 meta-llama
soulteary
└── ...
LinkSoul
└── ...
meta-llama
├── Llama-2-13b-chat-hf
│   ├── added_tokens.json
│   ├── config.json
│   ├── generation_config.json
│   ├── LICENSE.txt
│   ├── model-00001-of-00003.safetensors
│   ├── model-00002-of-00003.safetensors
│   ├── model-00003-of-00003.safetensors
│   ├── model.safetensors.index.json
│   ├── pytorch_model-00001-of-00003.bin
│   ├── pytorch_model-00002-of-00003.bin
│   ├── pytorch_model-00003-of-00003.bin
│   ├── pytorch_model.bin.index.json
│   ├── README.md
│   ├── Responsible-Use-Guide.pdf
│   ├── special_tokens_map.json
│   ├── tokenizer_config.json
│   ├── tokenizer.model
│   └── USE_POLICY.md
└── Llama-2-7b-chat-hf
    ├── added_tokens.json
    ├── config.json
    ├── generation_config.json
    ├── LICENSE.txt
    ├── model-00001-of-00002.safetensors
    ├── model-00002-of-00002.safetensors
    ├── model.safetensors.index.json
    ├── models--meta-llama--Llama-2-7b-chat-hf
    ├── pytorch_model-00001-of-00003.bin
    ├── pytorch_model-00002-of-00003.bin
    ├── pytorch_model-00003-of-00003.bin
    ├── pytorch_model.bin.index.json
    ├── README.md
    ├── special_tokens_map.json
    ├── tokenizer_config.json
    ├── tokenizer.json
    ├── tokenizer.model
    └── USE_POLICY.md
```

3. Run Llama2 model in docker command:

```bash
# 7B
bash scripts/run-7b.sh
# OR 13B
bash scripts/run-13b.sh
# OR Chinese 7B
bash scripts/run-7b-cn.sh
# OR Chinese 7B 4BIT
bash scripts/run-7b-cn-4bit.sh
```

enjoy, open `http://localhost7860` or `http://ip:7860` and play with the LLaMA2!


## Credit

- MetaAI LLaMA2: https://ai.meta.com/llama/ ❤️
- Meta LLaMA2 7B Chat: https://huggingface.co/meta-llama/Llama-2-7b-chat
- Meta LLaMA2 13B Chat: https://huggingface.co/meta-llama/Llama-2-13b-chat
- Chinese LLaMA2 7B: https://huggingface.co/LinkSoul/Chinese-Llama-2-7b ❤️
- Chinese LLaMA2 7B GGML q4: https://huggingface.co/soulteary/Chinese-Llama-2-7b-ggml-q4
- LLaMA2 GGML Converter: https://hub.docker.com/r/soulteary/llama2


================================================
FILE: docker/Dockerfile.13b
================================================
FROM soulteary/llama2:base

COPY llama2-13b/* ./

CMD ["python", "app.py"]

================================================
FILE: docker/Dockerfile.7b
================================================
FROM soulteary/llama2:base

COPY llama2-7b/* ./

CMD ["python", "app.py"]

================================================
FILE: docker/Dockerfile.7b-cn
================================================
FROM soulteary/llama2:base

COPY llama2-7b-cn/* ./

CMD ["python", "app.py"]

================================================
FILE: docker/Dockerfile.7b-cn-4bit
================================================
FROM soulteary/llama2:base

COPY llama2-7b-cn-4bit/* ./

CMD ["python", "app.py"]

================================================
FILE: docker/Dockerfile.base
================================================
FROM nvcr.io/nvidia/pytorch:23.06-py3
RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && \
    pip install accelerate==0.21.0 bitsandbytes==0.40.2 gradio==3.37.0 protobuf==3.20.3 scipy==1.11.1 sentencepiece==0.1.99 transformers==4.31.0
WORKDIR /app

================================================
FILE: llama.cpp/Dockerfile.converter
================================================
FROM alpine:3.18 as code
RUN apk add --no-cache wget
WORKDIR /app
ARG CODE_BASE=eb542d3
ENV ENV_CODE_BASE=${CODE_BASE}
RUN wget https://github.com/ggerganov/llama.cpp/archive/refs/tags/master-${ENV_CODE_BASE}.tar.gz && \
    tar zxvf master-${ENV_CODE_BASE}.tar.gz && \
    rm -rf master-${ENV_CODE_BASE}.tar.gz
RUN mv llama.cpp-master-${ENV_CODE_BASE} llama.cpp

FROM python:3.11.4-slim-bullseye as base
COPY --from=code /app/llama.cpp /app/llama.cpp
WORKDIR /app/llama.cpp
ENV DEBIAN_FRONTEND="noninteractive"
RUN apt-get update && apt-get install -y --no-install-recommends build-essential && rm -rf /var/lib/apt/lists/*
RUN make -j$(nproc)

FROM python:3.11.4-slim-bullseye as runtime
RUN pip3 install numpy==1.24 sentencepiece==0.1.98
COPY --from=base /app/llama.cpp/ /app/llama.cpp/
WORKDIR /app/llama.cpp/

================================================
FILE: llama.cpp/Dockerfile.runtime
================================================
FROM alpine:3.18 as code
RUN apk add --no-cache wget
WORKDIR /app
ARG CODE_BASE=d2a4366
ENV ENV_CODE_BASE=${CODE_BASE}
RUN wget https://github.com/ggerganov/llama.cpp/archive/refs/tags/master-${ENV_CODE_BASE}.tar.gz && \
    tar zxvf master-${ENV_CODE_BASE}.tar.gz && \
    rm -rf master-${ENV_CODE_BASE}.tar.gz
RUN mv llama.cpp-master-${ENV_CODE_BASE} llama.cpp

FROM python:3.11.4-slim-bullseye as base
COPY --from=code /app/llama.cpp /app/llama.cpp
WORKDIR /app/llama.cpp
ENV DEBIAN_FRONTEND="noninteractive"
RUN apt-get update && apt-get install -y --no-install-recommends build-essential && rm -rf /var/lib/apt/lists/*
RUN make -j$(nproc)

FROM python:3.11.4-slim-bullseye as runtime
COPY --from=base /app/llama.cpp/LICENSE /app/llama.cpp/LICENSE
COPY --from=base /app/llama.cpp/main /app/llama.cpp/main
COPY --from=base /app/llama.cpp/prompts /app/llama.cpp/prompts
WORKDIR /app/llama.cpp/

================================================
FILE: llama2-13b/app.py
================================================
from typing import Iterator

import gradio as gr
import torch

from model import run

DEFAULT_SYSTEM_PROMPT = """\
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.\n\nIf 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.\
"""
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024

DESCRIPTION = """
# Llama-2 13B Chat
This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
🔨 Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
🐇 For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
"""

LICENSE = """
<p/>
---
As a derivate work of [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta,
this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/USE_POLICY.md).
"""

if not torch.cuda.is_available():
    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'

def clear_and_save_textbox(message: str) -> tuple[str, str]:
    return '', message


def display_input(message: str,
                  history: list[tuple[str, str]]) -> list[tuple[str, str]]:
    history.append((message, ''))
    return history


def delete_prev_fn(
        history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
    try:
        message, _ = history.pop()
    except IndexError:
        message = ''
    return history, message or ''


def generate(
    message: str,
    history_with_input: list[tuple[str, str]],
    system_prompt: str,
    max_new_tokens: int,
    top_p: float,
    temperature: float,
    top_k: int,
) -> Iterator[list[tuple[str, str]]]:
    if max_new_tokens > MAX_MAX_NEW_TOKENS:
        raise ValueError

    history = history_with_input[:-1]
    generator = run(message, history, system_prompt, max_new_tokens,
                    temperature, top_p, top_k)
    try:
        first_response = next(generator)
        yield history + [(message, first_response)]
    except StopIteration:
        yield history + [(message, '')]
    for response in generator:
        yield history + [(message, response)]


def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
    generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 0.95, 1,
                         1000)
    for x in generator:
        pass
    return '', x


with gr.Blocks(css='style.css') as demo:
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(value='Duplicate Space for private use',
                       elem_id='duplicate-button')

    with gr.Group():
        chatbot = gr.Chatbot(label='Chatbot')
        with gr.Row():
            textbox = gr.Textbox(
                container=False,
                show_label=False,
                placeholder='Type a message...',
                scale=10,
            )
            submit_button = gr.Button('Submit',
                                      variant='primary',
                                      scale=1,
                                      min_width=0)
    with gr.Row():
        retry_button = gr.Button('🔄  Retry', variant='secondary')
        undo_button = gr.Button('↩️ Undo', variant='secondary')
        clear_button = gr.Button('🗑️  Clear', variant='secondary')

    saved_input = gr.State()

    with gr.Accordion(label='Advanced options', open=False):
        system_prompt = gr.Textbox(label='System prompt',
                                   value=DEFAULT_SYSTEM_PROMPT,
                                   lines=6)
        max_new_tokens = gr.Slider(
            label='Max new tokens',
            minimum=1,
            maximum=MAX_MAX_NEW_TOKENS,
            step=1,
            value=DEFAULT_MAX_NEW_TOKENS,
        )
        temperature = gr.Slider(
            label='Temperature',
            minimum=0.1,
            maximum=4.0,
            step=0.1,
            value=1.0,
        )
        top_p = gr.Slider(
            label='Top-p (nucleus sampling)',
            minimum=0.05,
            maximum=1.0,
            step=0.05,
            value=0.95,
        )
        top_k = gr.Slider(
            label='Top-k',
            minimum=1,
            maximum=1000,
            step=1,
            value=50,
        )

    gr.Examples(
        examples=[
            'Hello there! How are you doing?',
            'Can you explain briefly to me what is the Python programming language?',
            'Explain the plot of Cinderella in a sentence.',
            'How many hours does it take a man to eat a Helicopter?',
            "Write a 100-word article on 'Benefits of Open-Source in AI research'",
        ],
        inputs=textbox,
        outputs=[textbox, chatbot],
        fn=process_example,
        cache_examples=True,
    )
    gr.Markdown(LICENSE)

    textbox.submit(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    button_event_preprocess = submit_button.click(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    retry_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    undo_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=lambda x: x,
        inputs=[saved_input],
        outputs=textbox,
        api_name=False,
        queue=False,
    )

    clear_button.click(
        fn=lambda: ([], ''),
        outputs=[chatbot, saved_input],
        queue=False,
        api_name=False,
    )

demo.queue(max_size=20).launch(server_name="0.0.0.0")

================================================
FILE: llama2-13b/model.py
================================================
from threading import Thread
from typing import Iterator

import torch
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer

model_id = 'meta-llama/Llama-2-13b-chat-hf'

if torch.cuda.is_available():
    config = AutoConfig.from_pretrained(model_id)
    config.pretraining_tp = 1
    model = AutoModelForCausalLM.from_pretrained(
        model_id,
        local_files_only=True,
        config=config,
        torch_dtype=torch.float16,
        load_in_4bit=True,
        device_map='auto'
    )
else:
    model = None
tokenizer = AutoTokenizer.from_pretrained(model_id)


def get_prompt(message: str, chat_history: list[tuple[str, str]],
               system_prompt: str) -> str:
    texts = [f'[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
    for user_input, response in chat_history:
        texts.append(f'{user_input} [/INST] {response} [INST] ')
    texts.append(f'{message.strip()} [/INST]')
    return ''.join(texts)


def run(message: str,
        chat_history: list[tuple[str, str]],
        system_prompt: str,
        max_new_tokens: int = 1024,
        temperature: float = 0.8,
        top_p: float = 0.95,
        top_k: int = 50) -> Iterator[str]:
    prompt = get_prompt(message, chat_history, system_prompt)
    inputs = tokenizer([prompt], return_tensors='pt').to("cuda")

    streamer = TextIteratorStreamer(tokenizer,
                                    timeout=10.,
                                    skip_prompt=True,
                                    skip_special_tokens=True)
    generate_kwargs = dict(
        inputs,
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        top_p=top_p,
        top_k=top_k,
        temperature=temperature,
        num_beams=1,
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield ''.join(outputs)

================================================
FILE: llama2-7b/app.py
================================================
from typing import Iterator

import gradio as gr
import torch

from model import run

DEFAULT_SYSTEM_PROMPT = """\
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.\
"""
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024

DESCRIPTION = """
# Llama-2 7B Chat

This Space demonstrates model [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta, a Llama 2 model with 7B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).

🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).

🔨 Looking for an even more powerful model? Check out the [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
"""

LICENSE = """
<p/>

---
As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
"""

if not torch.cuda.is_available():
    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'


def clear_and_save_textbox(message: str) -> tuple[str, str]:
    return '', message


def display_input(message: str,
                  history: list[tuple[str, str]]) -> list[tuple[str, str]]:
    history.append((message, ''))
    return history


def delete_prev_fn(
        history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
    try:
        message, _ = history.pop()
    except IndexError:
        message = ''
    return history, message or ''


def generate(
    message: str,
    history_with_input: list[tuple[str, str]],
    system_prompt: str,
    max_new_tokens: int,
    top_p: float,
    temperature: float,
    top_k: int,
) -> Iterator[list[tuple[str, str]]]:
    if max_new_tokens > MAX_MAX_NEW_TOKENS:
        raise ValueError

    history = history_with_input[:-1]
    generator = run(message, history, system_prompt, max_new_tokens,
                    temperature, top_p, top_k)
    try:
        first_response = next(generator)
        yield history + [(message, first_response)]
    except StopIteration:
        yield history + [(message, '')]
    for response in generator:
        yield history + [(message, response)]


def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
    generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 0.95, 1,
                         1000)
    for x in generator:
        pass
    return '', x


with gr.Blocks(css='style.css') as demo:
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(value='Duplicate Space for private use',
                       elem_id='duplicate-button')

    with gr.Group():
        chatbot = gr.Chatbot(label='Chatbot')
        with gr.Row():
            textbox = gr.Textbox(
                container=False,
                show_label=False,
                placeholder='Type a message...',
                scale=10,
            )
            submit_button = gr.Button('Submit',
                                      variant='primary',
                                      scale=1,
                                      min_width=0)
    with gr.Row():
        retry_button = gr.Button('🔄  Retry', variant='secondary')
        undo_button = gr.Button('↩️ Undo', variant='secondary')
        clear_button = gr.Button('🗑️  Clear', variant='secondary')

    saved_input = gr.State()

    with gr.Accordion(label='Advanced options', open=False):
        system_prompt = gr.Textbox(label='System prompt',
                                   value=DEFAULT_SYSTEM_PROMPT,
                                   lines=6)
        max_new_tokens = gr.Slider(
            label='Max new tokens',
            minimum=1,
            maximum=MAX_MAX_NEW_TOKENS,
            step=1,
            value=DEFAULT_MAX_NEW_TOKENS,
        )
        temperature = gr.Slider(
            label='Temperature',
            minimum=0.1,
            maximum=4.0,
            step=0.1,
            value=1.0,
        )
        top_p = gr.Slider(
            label='Top-p (nucleus sampling)',
            minimum=0.05,
            maximum=1.0,
            step=0.05,
            value=0.95,
        )
        top_k = gr.Slider(
            label='Top-k',
            minimum=1,
            maximum=1000,
            step=1,
            value=50,
        )

    gr.Examples(
        examples=[
            'Hello there! How are you doing?',
            'Can you explain briefly to me what is the Python programming language?',
            'Explain the plot of Cinderella in a sentence.',
            'How many hours does it take a man to eat a Helicopter?',
            "Write a 100-word article on 'Benefits of Open-Source in AI research'",
        ],
        inputs=textbox,
        outputs=[textbox, chatbot],
        fn=process_example,
        cache_examples=True,
    )

    gr.Markdown(LICENSE)

    textbox.submit(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    button_event_preprocess = submit_button.click(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    retry_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    undo_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=lambda x: x,
        inputs=[saved_input],
        outputs=textbox,
        api_name=False,
        queue=False,
    )

    clear_button.click(
        fn=lambda: ([], ''),
        outputs=[chatbot, saved_input],
        queue=False,
        api_name=False,
    )

demo.queue(max_size=20).launch(server_name="0.0.0.0")



================================================
FILE: llama2-7b/model.py
================================================
from threading import Thread
from typing import Iterator

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer

model_id = 'meta-llama/Llama-2-7b-chat-hf'

if torch.cuda.is_available():
    model = AutoModelForCausalLM.from_pretrained(
        model_id,
        local_files_only=True,
        torch_dtype=torch.float16,
        device_map='auto'
    )
else:
    model = None
tokenizer = AutoTokenizer.from_pretrained(model_id)


def get_prompt(message: str, chat_history: list[tuple[str, str]],
               system_prompt: str) -> str:
    texts = [f'[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
    for user_input, response in chat_history:
        texts.append(f'{user_input.strip()} [/INST] {response.strip()} </s><s> [INST] ')
    texts.append(f'{message.strip()} [/INST]')
    return ''.join(texts)


def run(message: str,
        chat_history: list[tuple[str, str]],
        system_prompt: str,
        max_new_tokens: int = 1024,
        temperature: float = 0.8,
        top_p: float = 0.95,
        top_k: int = 50) -> Iterator[str]:
    prompt = get_prompt(message, chat_history, system_prompt)
    inputs = tokenizer([prompt], return_tensors='pt').to("cuda")

    streamer = TextIteratorStreamer(tokenizer,
                                    timeout=10.,
                                    skip_prompt=True,
                                    skip_special_tokens=True)
    generate_kwargs = dict(
        inputs,
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        top_p=top_p,
        top_k=top_k,
        temperature=temperature,
        num_beams=1,
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield ''.join(outputs)


================================================
FILE: llama2-7b-cn/app.py
================================================
from typing import Iterator

import gradio as gr
import torch

from model import run

DEFAULT_SYSTEM_PROMPT = """\
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.\
"""
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024

DESCRIPTION = """
# Llama-2 7B Chat (Chinese)

本空间是对于 [Chinese-Llama-2-7b](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b) 模型的演示。该模型由 LinkSoul 开发，基于 Llama 2 基础模型和自行收集的大规模中英文指令数据集 [instruction_merge_set](https://huggingface.co/datasets/LinkSoul/instruction_merge_set) 训练得到。

"""

LICENSE = """
<p/>

---
As a derivate work of [Chinese-Llama-2-7b](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b) by LinkSoul, [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
"""

if not torch.cuda.is_available():
    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'


def clear_and_save_textbox(message: str) -> tuple[str, str]:
    return '', message


def display_input(message: str,
                  history: list[tuple[str, str]]) -> list[tuple[str, str]]:
    history.append((message, ''))
    return history


def delete_prev_fn(
        history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
    try:
        message, _ = history.pop()
    except IndexError:
        message = ''
    return history, message or ''


def generate(
    message: str,
    history_with_input: list[tuple[str, str]],
    system_prompt: str,
    max_new_tokens: int,
    top_p: float,
    temperature: float,
    top_k: int,
) -> Iterator[list[tuple[str, str]]]:
    if max_new_tokens > MAX_MAX_NEW_TOKENS:
        raise ValueError

    history = history_with_input[:-1]
    generator = run(message, history, system_prompt, max_new_tokens,
                    temperature, top_p, top_k)
    try:
        first_response = next(generator)
        yield history + [(message, first_response)]
    except StopIteration:
        yield history + [(message, '')]
    for response in generator:
        yield history + [(message, response)]


def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
    generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 0.95, 1,
                         1000)
    for x in generator:
        pass
    return '', x


with gr.Blocks(css='style.css') as demo:
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(value='Duplicate Space for private use',
                       elem_id='duplicate-button')

    with gr.Group():
        chatbot = gr.Chatbot(label='Chatbot')
        with gr.Row():
            textbox = gr.Textbox(
                container=False,
                show_label=False,
                placeholder='Type a message...',
                scale=10,
            )
            submit_button = gr.Button('Submit',
                                      variant='primary',
                                      scale=1,
                                      min_width=0)
    with gr.Row():
        retry_button = gr.Button('🔄  Retry', variant='secondary')
        undo_button = gr.Button('↩️ Undo', variant='secondary')
        clear_button = gr.Button('🗑️  Clear', variant='secondary')

    saved_input = gr.State()

    with gr.Accordion(label='Advanced options', open=False):
        system_prompt = gr.Textbox(label='System prompt',
                                   value=DEFAULT_SYSTEM_PROMPT,
                                   lines=6)
        max_new_tokens = gr.Slider(
            label='Max new tokens',
            minimum=1,
            maximum=MAX_MAX_NEW_TOKENS,
            step=1,
            value=DEFAULT_MAX_NEW_TOKENS,
        )
        temperature = gr.Slider(
            label='Temperature',
            minimum=0.1,
            maximum=4.0,
            step=0.1,
            value=1.0,
        )
        top_p = gr.Slider(
            label='Top-p (nucleus sampling)',
            minimum=0.05,
            maximum=1.0,
            step=0.05,
            value=0.95,
        )
        top_k = gr.Slider(
            label='Top-k',
            minimum=1,
            maximum=1000,
            step=1,
            value=50,
        )

    gr.Examples(
        examples=[
            'Hello there! How are you doing?',
            'Can you explain briefly to me what is the Python programming language?',
            'Explain the plot of Cinderella in a sentence.',
            'How many hours does it take a man to eat a Helicopter?',
            "Write a 100-word article on 'Benefits of Open-Source in AI research'",
        ],
        inputs=textbox,
        outputs=[textbox, chatbot],
        fn=process_example,
        cache_examples=True,
    )

    gr.Markdown(LICENSE)

    textbox.submit(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    button_event_preprocess = submit_button.click(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    retry_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    undo_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=lambda x: x,
        inputs=[saved_input],
        outputs=textbox,
        api_name=False,
        queue=False,
    )

    clear_button.click(
        fn=lambda: ([], ''),
        outputs=[chatbot, saved_input],
        queue=False,
        api_name=False,
    )

demo.queue(max_size=20).launch(server_name="0.0.0.0")



================================================
FILE: llama2-7b-cn/model.py
================================================
from threading import Thread
from typing import Iterator

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer

model_id = 'LinkSoul/Chinese-Llama-2-7b'

if torch.cuda.is_available():
    model = AutoModelForCausalLM.from_pretrained(
        model_id,
        local_files_only=True,
        torch_dtype=torch.float16,
        device_map='auto'
    )
else:
    model = None
tokenizer = AutoTokenizer.from_pretrained(model_id)


def get_prompt(message: str, chat_history: list[tuple[str, str]],
               system_prompt: str) -> str:
    texts = [f'[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
    for user_input, response in chat_history:
        texts.append(f'{user_input.strip()} [/INST] {response.strip()} </s><s> [INST] ')
    texts.append(f'{message.strip()} [/INST]')
    return ''.join(texts)


def run(message: str,
        chat_history: list[tuple[str, str]],
        system_prompt: str,
        max_new_tokens: int = 1024,
        temperature: float = 0.8,
        top_p: float = 0.95,
        top_k: int = 50) -> Iterator[str]:
    prompt = get_prompt(message, chat_history, system_prompt)
    inputs = tokenizer([prompt], return_tensors='pt').to("cuda")

    streamer = TextIteratorStreamer(tokenizer,
                                    timeout=10.,
                                    skip_prompt=True,
                                    skip_special_tokens=True)
    generate_kwargs = dict(
        inputs,
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        top_p=top_p,
        top_k=top_k,
        temperature=temperature,
        num_beams=1,
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield ''.join(outputs)


================================================
FILE: llama2-7b-cn-4bit/app.py
================================================
from typing import Iterator

import gradio as gr
import torch

from model import run

DEFAULT_SYSTEM_PROMPT = """\
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.\
"""
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024

DESCRIPTION = """
# Llama-2 7B Chat (Chinese)

本空间是对于 [Chinese-Llama-2-7b-4bit](https://huggingface.co/soulteary/Chinese-Llama-2-7b-4bit) 模型的演示。该模型由 LinkSoul 开发，基于 Llama 2 基础模型和自行收集的大规模中英文指令数据集 [instruction_merge_set](https://huggingface.co/datasets/LinkSoul/instruction_merge_set) 训练得到。

"""

LICENSE = """
<p/>

---
As a derivate work of [Chinese-Llama-2-7b](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b) by LinkSoul, [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
"""

if not torch.cuda.is_available():
    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'


def clear_and_save_textbox(message: str) -> tuple[str, str]:
    return '', message


def display_input(message: str,
                  history: list[tuple[str, str]]) -> list[tuple[str, str]]:
    history.append((message, ''))
    return history


def delete_prev_fn(
        history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
    try:
        message, _ = history.pop()
    except IndexError:
        message = ''
    return history, message or ''


def generate(
    message: str,
    history_with_input: list[tuple[str, str]],
    system_prompt: str,
    max_new_tokens: int,
    top_p: float,
    temperature: float,
    top_k: int,
) -> Iterator[list[tuple[str, str]]]:
    if max_new_tokens > MAX_MAX_NEW_TOKENS:
        raise ValueError

    history = history_with_input[:-1]
    generator = run(message, history, system_prompt, max_new_tokens,
                    temperature, top_p, top_k)
    try:
        first_response = next(generator)
        yield history + [(message, first_response)]
    except StopIteration:
        yield history + [(message, '')]
    for response in generator:
        yield history + [(message, response)]


def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
    generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 0.95, 1,
                         1000)
    for x in generator:
        pass
    return '', x


with gr.Blocks(css='style.css') as demo:
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(value='Duplicate Space for private use',
                       elem_id='duplicate-button')

    with gr.Group():
        chatbot = gr.Chatbot(label='Chatbot')
        with gr.Row():
            textbox = gr.Textbox(
                container=False,
                show_label=False,
                placeholder='Type a message...',
                scale=10,
            )
            submit_button = gr.Button('Submit',
                                      variant='primary',
                                      scale=1,
                                      min_width=0)
    with gr.Row():
        retry_button = gr.Button('🔄  Retry', variant='secondary')
        undo_button = gr.Button('↩️ Undo', variant='secondary')
        clear_button = gr.Button('🗑️  Clear', variant='secondary')

    saved_input = gr.State()

    with gr.Accordion(label='Advanced options', open=False):
        system_prompt = gr.Textbox(label='System prompt',
                                   value=DEFAULT_SYSTEM_PROMPT,
                                   lines=6)
        max_new_tokens = gr.Slider(
            label='Max new tokens',
            minimum=1,
            maximum=MAX_MAX_NEW_TOKENS,
            step=1,
            value=DEFAULT_MAX_NEW_TOKENS,
        )
        temperature = gr.Slider(
            label='Temperature',
            minimum=0.1,
            maximum=4.0,
            step=0.1,
            value=1.0,
        )
        top_p = gr.Slider(
            label='Top-p (nucleus sampling)',
            minimum=0.05,
            maximum=1.0,
            step=0.05,
            value=0.95,
        )
        top_k = gr.Slider(
            label='Top-k',
            minimum=1,
            maximum=1000,
            step=1,
            value=50,
        )

    gr.Examples(
        examples=[
            'Hello there! How are you doing?',
            'Can you explain briefly to me what is the Python programming language?',
            'Explain the plot of Cinderella in a sentence.',
            'How many hours does it take a man to eat a Helicopter?',
            "Write a 100-word article on 'Benefits of Open-Source in AI research'",
        ],
        inputs=textbox,
        outputs=[textbox, chatbot],
        fn=process_example,
        cache_examples=True,
    )

    gr.Markdown(LICENSE)

    textbox.submit(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    button_event_preprocess = submit_button.click(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    retry_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    undo_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=lambda x: x,
        inputs=[saved_input],
        outputs=textbox,
        api_name=False,
        queue=False,
    )

    clear_button.click(
        fn=lambda: ([], ''),
        outputs=[chatbot, saved_input],
        queue=False,
        api_name=False,
    )

demo.queue(max_size=20).launch(server_name="0.0.0.0")



================================================
FILE: llama2-7b-cn-4bit/model.py
================================================
from threading import Thread
from typing import Iterator

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer

model_id = 'soulteary/Chinese-Llama-2-7b-4bit'

if torch.cuda.is_available():
    model = AutoModelForCausalLM.from_pretrained(
        model_id,
        load_in_4bit=True,
        local_files_only=True,
        torch_dtype=torch.float16,
        device_map='auto'
    )
else:
    model = None
tokenizer = AutoTokenizer.from_pretrained(model_id)


def get_prompt(message: str, chat_history: list[tuple[str, str]],
               system_prompt: str) -> str:
    texts = [f'[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
    for user_input, response in chat_history:
        texts.append(f'{user_input.strip()} [/INST] {response.strip()} </s><s> [INST] ')
    texts.append(f'{message.strip()} [/INST]')
    return ''.join(texts)


def run(message: str,
        chat_history: list[tuple[str, str]],
        system_prompt: str,
        max_new_tokens: int = 1024,
        temperature: float = 0.8,
        top_p: float = 0.95,
        top_k: int = 50) -> Iterator[str]:
    prompt = get_prompt(message, chat_history, system_prompt)
    inputs = tokenizer([prompt], return_tensors='pt').to("cuda")

    streamer = TextIteratorStreamer(tokenizer,
                                    timeout=10.,
                                    skip_prompt=True,
                                    skip_special_tokens=True)
    generate_kwargs = dict(
        inputs,
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        top_p=top_p,
        top_k=top_k,
        temperature=temperature,
        num_beams=1,
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield ''.join(outputs)


================================================
FILE: llama2-7b-cn-4bit/quantization_4bit.py
================================================
import torch
from transformers import AutoModelForCausalLM, BitsAndBytesConfig

# 使用中文版
model_id = 'LinkSoul/Chinese-Llama-2-7b'
# 或者，使用原版
# model_id = 'meta-llama/Llama-2-7b-chat-hf'

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    local_files_only=True,
    torch_dtype=torch.float16,
    quantization_config = BitsAndBytesConfig(
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype=torch.bfloat16
    ),
    device_map='auto'
)

import os
output = "soulteary/Chinese-Llama-2-7b-4bit"
if not os.path.exists(output):
    os.mkdir(output)

model.save_pretrained(output)
print("done")

================================================
FILE: scripts/make-13b.sh
================================================
#!/bin/bash

docker build -t soulteary/llama2:base . -f docker/Dockerfile.base

docker build -t soulteary/llama2:13b . -f docker/Dockerfile.13b


================================================
FILE: scripts/make-7b-cn-4bit.sh
================================================
#!/bin/bash

docker build -t soulteary/llama2:base . -f docker/Dockerfile.base

docker build -t soulteary/chinese-llama2:7b-4bit . -f docker/Dockerfile.7b-cn-4bit


================================================
FILE: scripts/make-7b-cn.sh
================================================
#!/bin/bash

docker build -t soulteary/llama2:base . -f docker/Dockerfile.base

docker build -t soulteary/llama2:7b-cn . -f docker/Dockerfile.7b-cn


================================================
FILE: scripts/make-7b.sh
================================================
#!/bin/bash

docker build -t soulteary/llama2:base . -f docker/Dockerfile.base

docker build -t soulteary/llama2:7b . -f docker/Dockerfile.7b


================================================
FILE: scripts/run-13b.sh
================================================
#!/bin/bash

docker run --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --rm -it -v `pwd`/meta-llama:/app/meta-llama -p 7860:7860 soulteary/llama2:13b


================================================
FILE: scripts/run-7b-cn-4bit.sh
================================================
#!/bin/bash

docker run --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --rm -it -v `pwd`/soulteary:/app/soulteary -p 7860:7860 soulteary/chinese-llama2:7b-4bit


================================================
FILE: scripts/run-7b-cn.sh
================================================
#!/bin/bash

docker run --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --rm -it -v `pwd`/LinkSoul:/app/LinkSoul -p 7860:7860 soulteary/llama2:7b-cn

================================================
FILE: scripts/run-7b.sh
================================================
#!/bin/bash

docker run --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --rm -it -v `pwd`/meta-llama:/app/meta-llama -p 7860:7860 soulteary/llama2:7b