srivatsavdamaraju commited on
Commit
8d7d685
·
verified ·
1 Parent(s): 0737dd8

Update Dockerfile

Browse files
Files changed (1) hide show
  1. Dockerfile +4 -4
Dockerfile CHANGED
@@ -2,13 +2,13 @@ FROM python:3.10-slim
2
 
3
  WORKDIR /app
4
 
5
- # Copy the model file into the container (adjust if model is in a subfolder)
6
- COPY SmolVLM-500M-Instruct.gguf /app/
7
 
8
  # Install llama-cpp-python with server
9
  RUN pip install --no-cache-dir llama-cpp-python[server]
10
 
11
  EXPOSE 8000
12
 
13
- # Run server with your GGUF model file
14
- CMD ["python", "-m", "llama_cpp.server", "--model", "SmolVLM-500M-Instruct.gguf"]
 
2
 
3
  WORKDIR /app
4
 
5
+ # Copy the exact model file into the container
6
+ COPY SmolVLM-500M-Instruct-Q8_0.gguf /app/
7
 
8
  # Install llama-cpp-python with server
9
  RUN pip install --no-cache-dir llama-cpp-python[server]
10
 
11
  EXPOSE 8000
12
 
13
+ # Run the server with your specific model filename
14
+ CMD ["python", "-m", "llama_cpp.server", "--model", "SmolVLM-500M-Instruct-Q8_0.gguf"]