Spaces:
Sleeping
Sleeping
Update Dockerfile
Browse files- 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
|
| 10 |
-
RUN pip install llama-cpp-python
|
|
|
|
|
|
|
|
|
|
| 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
|