|
FROM python:3.12 |
|
|
|
RUN useradd -m -u 1000 app |
|
|
|
WORKDIR /home/app |
|
|
|
RUN apt update |
|
RUN apt install -y wget make cmake clang git g++ |
|
RUN wget https://huggingface.co/mradermacher/bellman-mistral-7b-instruct-v0.3-GGUF/resolve/main/bellman-mistral-7b-instruct-v0.3.Q5_K_M.gguf?download=true -O model.gguf |
|
RUN git clone https://github.com/ggerganov/llama.cpp |
|
RUN mv llama.cpp llama_temp |
|
RUN mv llama_temp/* . |
|
RUN cmake -B build |
|
RUN cmake --build build --config Release |
|
|
|
|
|
|
|
|
|
EXPOSE 7860 |
|
|
|
CMD ["sh", "-c", "./build/bin/llama-server -m /home/app/model.gguf -c 4096 -n 1024 --host 0.0.0.0 --port 7860"] |
