File size: 375 Bytes
0737dd8
e1fa655
0737dd8
3a7f2f0
8d7d685
 
3a7f2f0
0737dd8
 
3a7f2f0
0737dd8
3a7f2f0
8d7d685
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
FROM python:3.10-slim

WORKDIR /app

# Copy the exact model file into the container
COPY SmolVLM-500M-Instruct-Q8_0.gguf /app/

# Install llama-cpp-python with server
RUN pip install --no-cache-dir llama-cpp-python[server]

EXPOSE 8000

# Run the server with your specific model filename
CMD ["python", "-m", "llama_cpp.server", "--model", "SmolVLM-500M-Instruct-Q8_0.gguf"]