Create app.py

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from llama_cpp import Llama
+
+# 初始化模型
+MODEL_PATH = "models/qwen2.5-0.5b-instruct-q5_k_m.gguf"
+
+llm = Llama(
+    model_path=MODEL_PATH,
+    n_ctx=2048,
+    n_gpu_layers=0,
+)
+
+def chat(user_input):
+    prompt = f"User: {user_input}\nAssistant: "
+    output = llm(
+        prompt=prompt,
+        temperature=0.7,
+        top_p=0.9,
+        max_tokens=100
+    )
+    response_text = output['choices'][0]['text'].strip()
+    return response_text
+
+# 创建 Gradio 接口
+iface = gr.Interface(
+    fn=chat,
+    inputs="text",
+    outputs="text",
+    title="Qwen Chatbot",
+    description="与 Qwen2.5-0.5B-Instruct-GGUF 模型对话"
+)
+
+iface.launch()