Create app.py

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# 加载Qwen1.5-7B-Chat模型
+model_name = "Qwen/Qwen1.5-7B-Chat"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"  
+)
+
+
+def chat_with_qwen(message):
+    
+    messages = [{"role": "user", "content": message}]
+    inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+    
+  
+    outputs = model.generate(
+        inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.95
+    )
+    response = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)
+    return response
+
+
+iface = gr.Interface(
+    fn=chat_with_qwen,
+    inputs=gr.Textbox(lines=2, placeholder="输入你的消息..."),
+    outputs="text",
+    title="Qwen Chatbot API",
+    description="基于Qwen1.5-7B-Chat的中文优化聊天机器人"
+)
+
+iface.launch(server_name="0.0.0.0", server_port=7860)