利用text-generation-webui快速搭建chatGLM2/LLAMA2大模型运行环境

text-generation-webui 是一个基于Gradio的LLM Web UI开源项目，可以利用其快速搭建各种文本生成的大模型环境。

一、安装

text-generation-webui的readme其实已写得相当详细了，这里就不再重复，只说1个可能存在的坑：

安装 peft 安装卡住

requirements.txt 中有一些依赖项，需要访问github网站，国内经常会打不开，看看这个文件的内容：

aiofiles==23.1.0
fastapi==0.95.2
gradio_client==0.2.5
gradio==3.33.1

accelerate==0.21.0
colorama
datasets
einops
markdown
numpy
pandas
Pillow>=9.5.0
pyyaml
requests
safetensors==0.3.1
scipy
sentencepiece
tensorboard
tqdm
wandb

git+https://github.com/huggingface/peft@4b371b489b9850fd583f204cdf8b5471e098d4e4
git+https://github.com/huggingface/transformers@baf1daa58eb2960248fd9f7c3af0ed245b8ce4af

bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.1/auto_gptq-0.4.1+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.1/auto_gptq-0.4.1+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/exllama/releases/download/0.0.10/exllama-0.0.10+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/exllama/releases/download/0.0.10/exllama-0.0.10+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

# llama-cpp-python without GPU support
llama-cpp-python==0.1.78; platform_system != "Windows"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.1.78/llama_cpp_python-0.1.78-cp310-cp310-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python with CUDA support
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.1.78+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.1.78+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

# GPTQ-for-LLaMa
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

# ctransformers
https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.22+cu117-py3-none-any.whl

如果安装peft时，项目无法下载，可以把这行注释掉。然后再开1个终端，直接用

pip install peft -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install transformers -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install accelerate -i  https://pypi.tuna.tsinghua.edu.cn/simple

走国内镜像安装，然后再回到原来的终端 pip install -r requirements.txt, 其它依赖项，也是这个思路。

二、启动及model下载

python server.py 即可启动，刚启动时没有任何模型，需要手动下载。

huggingface.co的模型，只要允许下载的，text-generation-webui都能下载，不过这个速度比较慢，而且容易中断，我个人更建议手动下载（比如 git LFS工具，或者国内有一些镜像或网盘上，有热心网友上传了副本），如果是手动下载，只要把模型放到 text-generation-webui/models 目录下即可。

三、加载模型

3.1 Llam2 模型加载

这里选择 TheBloke/Llama-2-7B-Chat-GGML · Hugging Face 这个Llama2模型测试，选择后发现自动默认用了llama.cpp 这个c++版本的loader（注：c++版本的推理速度更快)