download llama

Dockerfile

@@ -18,8 +18,6 @@ RUN pip install accelerate
 
 # Install hugging face hub to download llama2 model
 RUN pip install --upgrade huggingface_hub
-RUN huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
-
 RUN CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install 'llama-cpp-python[server]' --upgrade --force-reinstall --no-cache-dir 
 # Install requirements.txt 
 RUN pip install --no-cache-dir --upgrade -r /requirements.txt
@@ -34,6 +32,9 @@ ENV HOME=/home/user \
 
 WORKDIR $HOME/app
 
+RUN huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+
+
 COPY --chown=user . $HOME/app
 
 # Start the FastAPI app on port 7860, the default port expected by Spaces