feat: 添加基于SmolLM2-135M的Gradio聊天界面

实现一个完整的聊天助手界面，包含以下功能：
- 后台线程加载模型
- 可调节生成参数（temperature, max_length, top_p）
- 聊天历史记录功能
- 错误处理和状态提示

app.py

@@ -1,10 +1,137 @@
-# pip install transformers
+import torch
+import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import threading
+import time
+
+# Global variables for model and tokenizer
+model = None
+tokenizer = None
+model_loaded = False
 checkpoint = "HuggingFaceTB/SmolLM2-135M"
-device = "cuda" # for GPU usage or "cpu" for CPU usage
-tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
-model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
-inputs = tokenizer.encode("Gravity is", return_tensors="pt").to(device)
-outputs = model.generate(inputs)
-print(tokenizer.decode(outputs[0]))
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+def load_model():
+    """Load the model and tokenizer"""
+    global model, tokenizer, model_loaded
+    try:
+        print("Loading model...")
+        tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+        model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+        model_loaded = True
+        print("Model loaded successfully!")
+    except Exception as e:
+        print(f"Error loading model: {e}")
+        model_loaded = False
+
+def generate_response(message, history, temperature, max_length, top_p):
+    """Generate response from the model"""
+    global model, tokenizer, model_loaded
+    
+    if not model_loaded:
+        return "模型尚未加载完成，请稍等..."
+    
+    try:
+        # Tokenize input
+        inputs = tokenizer.encode(message, return_tensors="pt").to(device)
+        
+        # Generate
+        with torch.no_grad():
+            outputs = model.generate(
+                inputs,
+                max_length=max_length,
+                temperature=temperature,
+                top_p=top_p,
+                do_sample=True,
+                pad_token_id=tokenizer.eos_token_id
+            )
+        
+        # Decode response
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return response.strip()
+        
+    except Exception as e:
+        return f"生成回复时出错: {str(e)}"
+
+def chat_interface(message, history, temperature, max_length, top_p):
+    """Chat interface for Gradio"""
+    response = generate_response(message, history, temperature, max_length, top_p)
+    history.append([message, response])
+    return "", history
+
+# Load model in background
+loading_thread = threading.Thread(target=load_model)
+loading_thread.start()
+
+# Create Gradio interface
+with gr.Blocks(title="AI Chat Assistant") as demo:
+    gr.Markdown("# 🤖 AI Chat Assistant")
+    gr.Markdown("基于 SmolLM2-135M 模型的聊天助手")
+    
+    with gr.Row():
+        with gr.Column(scale=3):
+            chatbot = gr.Chatbot(
+                value=[],
+                height=500,
+                show_label=False
+            )
+            
+            with gr.Row():
+                msg = gr.Textbox(
+                    placeholder="输入您的消息...",
+                    show_label=False,
+                    scale=4
+                )
+                send_btn = gr.Button("发送", scale=1)
+            
+            clear_btn = gr.Button("清空对话")
+        
+        with gr.Column(scale=1):
+            gr.Markdown("### 参数设置")
+            temperature = gr.Slider(
+                minimum=0.1,
+                maximum=2.0,
+                value=0.7,
+                step=0.1,
+                label="Temperature"
+            )
+            max_length = gr.Slider(
+                minimum=100,
+                maximum=2000,
+                value=1000,
+                step=100,
+                label="最大长度"
+            )
+            top_p = gr.Slider(
+                minimum=0.1,
+                maximum=1.0,
+                value=0.95,
+                step=0.05,
+                label="Top-p"
+            )
+    
+    # Event handlers
+    send_btn.click(
+        chat_interface,
+        inputs=[msg, chatbot, temperature, max_length, top_p],
+        outputs=[msg, chatbot]
+    )
+    
+    msg.submit(
+        chat_interface,
+        inputs=[msg, chatbot, temperature, max_length, top_p],
+        outputs=[msg, chatbot]
+    )
+    
+    clear_btn.click(
+        lambda: ([], ""),
+        outputs=[chatbot, msg]
+    )
+
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True,
+        show_error=True
+    )