Deploy FastAPI server with CodeLlama 7B

requirements.txt

@@ -1,3 +1,7 @@
-gradio==4.19.0
-huggingface-hub
-llama-cpp-python @ https://github.com/zckly/llama-cpp-python-manylinux-wheel/releases/download/llama_cpp_python-0.3.15/llama_cpp_python-0.3.15-cp310-cp310-manylinux_2_31_x86_64.whl
+--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+llama-cpp-python>=0.2.0
+fastapi>=0.104.0
+uvicorn[standard]>=0.24.0
+pydantic>=2.0.0
+huggingface-hub>=0.19.0
+python-multipart