from llama_cpp import Llama

llm = Llama(
    model_path="Llama-3-Open-Ko-8B-Q4_K_M.gguf",
    n_ctx=2048,
    n_gpu_layers=0
)

response = llm("안녕하세요")
print(response)

"""

README 업로드

Base Model: <a href="https://huggingface.co/beomi/Llama-3-Open-Ko-8B" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">beomi/Llama-3-Open-Ko-8B
양자화: Q4_K_M
크기: ~4.5GB
용도: RFPilot 프로젝트 Base 모델 비교용

upload_file( path_or_fileobj=readme_content.encode(), path_in_repo="README.md", repo_id="Dongjin1203/Llama-3-Open-Ko-8B-GGUF", repo_type="model" )