tweak

Dockerfile

@@ -1,25 +1,10 @@
-# Use the Python 3.11 base image
 FROM python:3.11
 
-# Set the working directory
 WORKDIR /usr/src/app
-
-# Copy the application code into the container
 COPY . .
-
-# Install the Python dependencies from requirements.txt
 RUN pip install -r requirements.txt
 
-# Install huggingface-cli
-RUN pip install huggingface-cli
-
-# Expose the port on which your Gradio app runs
 EXPOSE 7860
-
-# Set an environment variable for the Gradio server name
 ENV GRADIO_SERVER_NAME="0.0.0.0"
 
-# Define an entrypoint script to run both commands
-COPY entrypoint.sh /usr/src/app/entrypoint.sh
-RUN chmod +x /usr/src/app/entrypoint.sh
-ENTRYPOINT ["/usr/src/app/entrypoint.sh"]
+CMD ["python", "app.py"]

app.py

@@ -6,6 +6,14 @@ from huggingface_hub import hf_hub_download
 
 # huggingface-cli download microsoft/Phi-3-mini-4k-instruct-gguf Phi-3-mini-4k-instruct-q4.gguf --local-dir .
 # huggingface-cli download LoneStriker/OpenBioLLM-Llama3-8B-GGUF --local-dir ./llama3-gguf
+
+model_name = "aaditya/OpenBioLLM-Llama3-8B-GGUF"
+model_file = "openbiollm-llama3-8b.Q5_K_M.gguf"
+
+model_path = hf_hub_download(model_name,
+                             filename=model_file,
+                             local_dir='/llama3-gguf')
+
 llm = Llama(
     # model_path="./Phi-3-mini-4k-instruct-q4.gguf",
     model_path="./llama3-gguf/OpenBioLLM-Llama3-8B-Q5_K_M.gguf",