Update app.py

app.py

@@ -5,48 +5,53 @@ from transformers import AutoTokenizer, pipeline
 
 # 載入模型和標記器
 model_id = "hsuwill000/DeepSeek-R1-Distill-Qwen-1.5B-openvino"
+print("Loading model...")
 model = OVModelForCausalLM.from_pretrained(model_id, device_map="auto")
+print("Loading tokenizer...")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-# 建立生成管道
-#pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
-
-def respond(prompt , history):
-    # 將當前訊息與歷史訊息合併
-    #input_text = message if not history else history[-1]["content"] + " " + message
-    #input_text = message+",(450字內回覆)"
-    
+def respond(prompt, history):
+    # 構建聊天模板
     messages = [
-    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
-    {"role": "user", "content": prompt }
+        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+        {"role": "user", "content": prompt}
     ]
     text = tokenizer.apply_chat_template(
         messages,
         tokenize=False,
         add_generation_prompt=True
     )
-    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)    
+    print("Chat template text:", text)
+
+    # 將文本轉換為模型輸入
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+    print("Model inputs:", model_inputs)
+
+    # 生成回應
     generated_ids = model.generate(
         **model_inputs,
         max_new_tokens=512
-    )    
-    
-    # 獲取模型的回應
-    #response = pipe(input_text, max_length=512, truncation=True, num_return_sequences=1)
-    #reply = response[0]['generated_text']
+    )
+    print("Generated IDs:", generated_ids)
+
+    # 解碼生成的 token IDs
     generated_ids = [
         output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
     ]
-    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]    
-    
-    # 返回新的消息格式
-    print(f"Messages: {messages}")
-    print(f"Reply: {response}")
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    print("Decoded response:", response)
+
+    # 返回回應
     return response
-    
+
 # 設定 Gradio 的聊天界面
-demo = gr.ChatInterface(fn=respond, title="Qwen2.5-0.5B-Instruct-openvino-4bit", description="Qwen2.5-0.5B-Instruct-openvino-4bit", type='messages')
+demo = gr.ChatInterface(
+    fn=respond,
+    title="Qwen2.5-0.5B-Instruct-openvino-4bit",
+    description="Qwen2.5-0.5B-Instruct-openvino-4bit"
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    print("Launching Gradio app...")
+    demo.launch(server_name="0.0.0.0", server_port=7860)