tweak 7

Dockerfile

@@ -1,13 +1,31 @@
 FROM python:3.11
 
-WORKDIR /usr/src/app
-COPY . .
-RUN pip install -r requirements.txt
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+
 
 EXPOSE 7860
 ENV GRADIO_SERVER_NAME="0.0.0.0"
 
-# Specify a non-root user
-USER appuser
+
+# Download a checkpoint
+RUN mkdir content
+ADD --chown=user  https://huggingface.co/NicholasJohn/OpenBioLLM-Llama3-8B-Q5_K_M.gguf/blob/main/OpenBioLLM-Llama3-8B-Q5_K_M.gguf content/OpenBioLLM-Llama3-8B-Q5_K_M.gguf
+
+
+RUN pip install -r requirements.txt
 
 CMD ["python", "app.py"]

app.py

@@ -11,10 +11,7 @@ from huggingface_hub.file_download import http_get
 llm = Llama(
     # model_path="./Phi-3-mini-4k-instruct-q4.gguf",
     # model_path="./llama3-gguf/OpenBioLLM-Llama3-8B-Q5_K_M.gguf",
-    model_path = hf_hub_download(
-        repo_id=os.environ.get("REPO_ID", "LoneStriker/OpenBioLLM-Llama3-8B-GGUF"),
-        filename=os.environ.get("MODEL_FILE", "Llama3-8B-Q5_K_M.gguf"),
-    ),
+    model_path = "content/OpenBioLLM-Llama3-8B-Q5_K_M.gguf",
     n_ctx=2048,
     n_gpu_layers=50, # change n_gpu_layers if you have more or less VRAM 
 )