Upload Dockerfile with huggingface_hub

Dockerfile

@@ -5,15 +5,15 @@ FROM vllm/vllm-openai:v0.6.6.post1
 # Set environment variables
 ENV MODEL_NAME="TheBloke/Llama-2-7B-Chat-AWQ"
 ENV HOST="0.0.0.0"
-ENV PORT="8000"
+ENV PORT="7860"
 
 # Expose the API port
-EXPOSE 8000
+EXPOSE 7860
 
 # Run vLLM OpenAI-compatible server
 ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
 CMD ["--model", "TheBloke/Llama-2-7B-Chat-AWQ", \
      "--quantization", "awq", \
      "--host", "0.0.0.0", \
-     "--port", "8000", \
+     "--port", "7860", \
      "--max-model-len", "4096"]