Update app.py

app.py

@@ -1,35 +1,25 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 from optimum.intel import OVModelForCausalLM
 from transformers import AutoTokenizer, pipeline
 
+# 載入模型和標記器
 model_id = "HelloSun/Qwen2.5-0.5B-Instruct-openvino"
 model = OVModelForCausalLM.from_pretrained(model_id)
-
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
-
-
-def respond(
-    message,
-    history,
-):
-    print(message,history)
-    return pipe(message)
-    
 
+# 建立生成管道
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-)
+def respond(message, history):
+    # 將當前訊息與歷史訊息合併
+    input_text = message if not history else history[-1][1] + " " + message
+    # 獲取模型的回應
+    response = pipe(input_text, max_length=100, num_return_sequences=1)
+    return response[0]['generated_text'], history + [(message, response[0]['generated_text'])]
 
+# 設定 Gradio 的聊天界面
+demo = gr.ChatInterface(fn=respond)
 
 if __name__ == "__main__":
     demo.launch()