Upload Dockerfile

Dockerfile

@@ -36,4 +36,4 @@ EXPOSE 7860
 ENTRYPOINT []
 
 # Set the CMD to launch the vLLM server (for your new model) in the background and then start the Gradio app.
-CMD ["bash", "-c", "vllm.entrypoints.openai.api_server --model unsloth/llama-3-8b-Instruct-bnb-4bit --enable-auto-tool-choice --tool-call-parser llama3_json --chat-template examples/tool_chat_template_llama3.1_json.jinja --quantization bitsandbytes --load-format bitsandbytes --dtype half --max-model-len 8192 > /app/vllm.log 2>&1 & python3 app.py"]
+CMD ["bash", "-c", "vllm.entrypoints.openai.api_server --model unsloth/llama-3-8b-Instruct-bnb-4bit --enable-auto-tool-choice --tool-call-parser llama3_json --chat-template examples/tool_chat_template_llama3.1_json.jinja --quantization bitsandbytes --load-format bitsandbytes --dtype half --max-model-len 8192 python3 app.py"]