| from llama_cpp import Llama | |
| # 直接从 Hugging Face 加载模型（避免存储问题） | |
| llm = Llama.from_pretrained("YLX1965/medical-model", filename="unsloth.Q8_0.gguf") | |
| def chat(prompt): | |
| output = llm(prompt, max_tokens=200) | |
| return output["choices"][0]["text"] | |
| # 运行 Gradio | |
| import gradio as gr | |
| interface = gr.Interface(fn=chat, inputs="text", outputs="text") | |
| interface.launch() |