사용할 llm모델

https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M

pip install llama-cpp-python --no-cache-dir

CMAKE_ARGS="-DLLAMA_CUDA=on" pip install llama-cpp-python --no-cache-dir --force-reinstall