Fix Gradio compatibility issues and startup configuration

app.py

@@ -3,6 +3,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 from peft import PeftModel
 import warnings
+import os
 warnings.filterwarnings("ignore")
 
 # 模型配置
@@ -64,7 +65,7 @@ def generate_response(prompt, max_tokens=200, temperature=0.7, top_p=0.9):
         return "❌ Model not loaded. Please check the logs or try again."
     
     try:
-        # 格式化输入 - 移除多余的字符串插值
+        # 格式化输入
         formatted_prompt = prompt.strip()
         
         # 编码输入
@@ -114,105 +115,68 @@ def chat_interface(message, history, max_tokens, temperature, top_p):
         history.append((message, error_msg))
         return history, ""
 
-# 创建 Gradio 应用
-with gr.Blocks(title="Robot Task Planning - Llama 3.1 8B", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("""
-    # 🤖 Llama 3.1 8B - Robot Task Planning
-    
-    This is a fine-tuned version of Meta's Llama 3.1 8B model specialized for **robot task planning** using QLoRA technique.
-    
-    **Capabilities**: Convert natural language robot commands into structured task sequences for excavators, dump trucks, and other construction robots.
-    
-    **Model**: [YongdongWang/llama-3.1-8b-dart-qlora](https://huggingface.co/YongdongWang/llama-3.1-8b-dart-qlora)
-    
-    ⚠️ **Note**: Model loading may take a few minutes on first startup.
-    """)
-    
-    with gr.Row():
-        with gr.Column(scale=3):
-            chatbot = gr.Chatbot(
-                label="Task Planning Results",
-                height=400,
-                show_label=True,
-                container=True,
-                bubble_full_width=False
-            )
-            
-            msg = gr.Textbox(
-                label="Robot Command",
-                placeholder="Enter robot task command (e.g., 'Deploy Excavator 1 to Soil Area 1')...",
-                lines=2,
-                max_lines=5,
-                show_label=True,
-                container=True
-            )
-            
-            with gr.Row():
-                send_btn = gr.Button("Generate Tasks", variant="primary", size="sm")
-                clear_btn = gr.Button("Clear", variant="secondary", size="sm")
+# 创建 Gradio 应用 - 简化版本以避免兼容性问题
+def create_interface():
+    with gr.Blocks(title="Robot Task Planning - Llama 3.1 8B") as demo:
+        gr.Markdown("""
+        # 🤖 Llama 3.1 8B - Robot Task Planning
         
-        with gr.Column(scale=1):
-            gr.Markdown("### ⚙️ Generation Settings")
-            
-            max_tokens = gr.Slider(
-                minimum=50,
-                maximum=500,
-                value=200,
-                step=10,
-                label="Max Tokens",
-                info="Maximum number of tokens to generate"
-            )
-            
-            temperature = gr.Slider(
-                minimum=0.1,
-                maximum=2.0,
-                value=0.7,
-                step=0.1,
-                label="Temperature",
-                info="Controls randomness (lower = more focused)"
-            )
+        This is a fine-tuned version of Meta's Llama 3.1 8B model specialized for **robot task planning** using QLoRA technique.
+        
+        **Model**: [YongdongWang/llama-3.1-8b-dart-qlora](https://huggingface.co/YongdongWang/llama-3.1-8b-dart-qlora)
+        
+        ⚠️ **Note**: Model loading may take a few minutes on first startup.
+        """)
+        
+        # 聊天界面
+        chatbot = gr.Chatbot(label="Task Planning Results", height=400)
+        msg = gr.Textbox(
+            label="Robot Command",
+            placeholder="Enter robot task command (e.g., 'Deploy Excavator 1 to Soil Area 1')...",
+            lines=2
+        )
+        
+        # 控制按钮
+        with gr.Row():
+            send_btn = gr.Button("Generate Tasks", variant="primary")
+            clear_btn = gr.Button("Clear")
+        
+        # 生成参数 - 简化版本
+        with gr.Accordion("⚙️ Generation Settings", open=False):
+            max_tokens = gr.Slider(50, 500, 200, label="Max Tokens")
+            temperature = gr.Slider(0.1, 2.0, 0.7, label="Temperature")
+            top_p = gr.Slider(0.1, 1.0, 0.9, label="Top-p")
+        
+        # 示例 - 简化版本
+        with gr.Accordion("💡 Example Commands", open=False):
+            examples = [
+                "Deploy Excavator 1 to Soil Area 1 for excavation.",
+                "Send Dump Truck 1 to collect material, then unload at storage area.",
+                "Move all robots to avoid Puddle 1 after inspection.",
+                "Deploy multiple excavators to different soil areas simultaneously.",
+                "Coordinate dump trucks to transport materials from excavation site to storage.",
+            ]
             
-            top_p = gr.Slider(
-                minimum=0.1,
-                maximum=1.0,
-                value=0.9,
-                step=0.05,
-                label="Top-p",
-                info="Nucleus sampling threshold"
-            )
-    
-    # 示例对话
-    gr.Examples(
-        examples=[
-            ["Deploy Excavator 1 to Soil Area 1 for excavation."],
-            ["Send Dump Truck 1 to collect material, then unload at storage area."],
-            ["Move all robots to avoid Puddle 1 after inspection."],
-            ["Deploy multiple excavators to different soil areas simultaneously."],
-            ["Coordinate dump trucks to transport materials from excavation site to storage."],
-            ["Send robot to inspect rock area, then avoid with all other robots."],
-            ["Return all robots to start position after completing tasks."],
-        ],
-        inputs=msg,
-        label="💡 Example Robot Commands"
-    )
-    
-    # 事件处理
-    msg.submit(
-        chat_interface,
-        inputs=[msg, chatbot, max_tokens, temperature, top_p],
-        outputs=[chatbot, msg]
-    )
-    
-    send_btn.click(
-        chat_interface,
-        inputs=[msg, chatbot, max_tokens, temperature, top_p],
-        outputs=[chatbot, msg]
-    )
+            for example in examples:
+                example_btn = gr.Button(example, size="sm")
+                example_btn.click(lambda x=example: x, outputs=msg)
+        
+        # 事件处理
+        def submit_message(message, history, max_tokens, temperature, top_p):
+            return chat_interface(message, history, max_tokens, temperature, top_p)
+        
+        msg.submit(submit_message, [msg, chatbot, max_tokens, temperature, top_p], [chatbot, msg])
+        send_btn.click(submit_message, [msg, chatbot, max_tokens, temperature, top_p], [chatbot, msg])
+        clear_btn.click(lambda: ([], ""), outputs=[chatbot, msg])
     
-    clear_btn.click(
-        lambda: ([], ""),
-        outputs=[chatbot, msg]
-    )
+    return demo
 
 if __name__ == "__main__":
-    demo.launch()
+    demo = create_interface()
+    # 修复启动配置 - 关键修复！
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True,  # 这是关键！
+        show_error=True
+    )

requirements.txt

@@ -1,7 +1,8 @@
-gradio==4.44.0
+gradio==4.20.0
 transformers==4.44.2
 torch==2.1.0
 peft==0.7.1
 bitsandbytes==0.41.3
 accelerate==0.24.1
 scipy==1.11.4
+packaging