update app.py

app.py

@@ -1,11 +1,31 @@
 import gradio as gr
+import os
+import requests
 from llama_cpp import Llama
 
-# 加载 GGUF 模型（替换成你的模型路径）
-model_path = "YLX1965/medical-model/unsloth.Q8_0.gguf"
+# 确保模型文件夹存在
+model_dir = "/home/user/models"
+os.makedirs(model_dir, exist_ok=True)
 
+# GGUF 模型文件名
+model_name = "unsloth.Q8_0.gguf"
+model_path = os.path.join(model_dir, model_name)
+
+# 如果模型文件不存在，则从 Hugging Face 下载
+hf_model_url = "https://huggingface.co/YLX1965/medical-model/resolve/main/unsloth.Q8_0.gguf"
+
+if not os.path.exists(model_path):
+    print(f"Downloading model from {hf_model_url}...")
+    response = requests.get(hf_model_url, stream=True)
+    with open(model_path, "wb") as f:
+        for chunk in response.iter_content(chunk_size=8192):
+            f.write(chunk)
+    print("Download complete.")
+
+# 加载 GGUF 模型
 llm = Llama(model_path=model_path)
 
+# 定义聊天函数
 def chat(prompt):
     output = llm(prompt, max_tokens=200)
     return output["choices"][0]["text"]