visamram02 commited on
Commit
ee5b434
·
verified ·
1 Parent(s): dfef1eb

Update Dockerfile

Browse files
Files changed (1) hide show
  1. Dockerfile +5 -2
Dockerfile CHANGED
@@ -6,8 +6,11 @@ RUN apt-get update && apt-get install -y \
6
  wget \
7
  && rm -rf /var/lib/apt/lists/*
8
 
9
- # Install llama-cpp-python with server extra using pre-built wheels to avoid timeout
10
- RUN pip install llama-cpp-python[server] --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
 
 
11
 
12
  # Download the model (Qwen 2.5 7B Instruct Quantized)
13
  RUN wget https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-GGUF/resolve/main/qwen2.5-7b-instruct-q4_k_m.gguf -O model.gguf
 
6
  wget \
7
  && rm -rf /var/lib/apt/lists/*
8
 
9
+ # Install llama-cpp-python from pre-built wheel (Luigi repo)
10
+ RUN pip install https://huggingface.co/Luigi/llama-cpp-python-wheels-hf-spaces-free-cpu/resolve/main/llama_cpp_python-0.3.16-cp310-cp310-linux_x86_64.whl
11
+
12
+ # Install server dependencies manually
13
+ RUN pip install uvicorn anyio starlette sse-starlette fastapi pydantic-settings diskcache jinja2 numpy
14
 
15
  # Download the model (Qwen 2.5 7B Instruct Quantized)
16
  RUN wget https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-GGUF/resolve/main/qwen2.5-7b-instruct-q4_k_m.gguf -O model.gguf