# 从NVIDIA源，从而支持显卡运损（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
FROM nvidia/cuda:11.3.1-runtime-ubuntu20.04
ARG useProxyNetwork=''
RUN apt-get update
RUN apt-get install -y curl proxychains curl 
RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing


# use python3 as the system default python
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
# 下载pytorch
RUN python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
# 下载分支
WORKDIR /gpt
RUN git clone https://github.com/binary-husky/chatgpt_academic.git
WORKDIR /gpt/chatgpt_academic
RUN git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss
RUN python3 -m pip install -r requirements.txt
RUN python3 -m pip install -r request_llm/requirements_moss.txt
RUN python3 -m pip install -r request_llm/requirements_chatglm.txt
RUN python3 -m pip install -r request_llm/requirements_newbing.txt

# 预热CHATGLM参数（非必要 可选步骤）
RUN echo ' \n\
from transformers import AutoModel, AutoTokenizer \n\
chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) \n\
chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float() ' >> warm_up_chatglm.py
RUN python3 -u warm_up_chatglm.py

# 禁用缓存，确保更新代码
ADD "https://www.random.org/cgi-bin/randbyte?nbytes=10&format=h" skipcache
RUN git pull

# 预热Tiktoken模块
RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'

# 启动
CMD ["python3", "-u", "main.py"]