Update app.py

app.py

@@ -8,51 +8,36 @@ perplexity = evaluate.load("perplexity", module_type="metric")
 # 创建推理客户端
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
-    messages = [{"role": "system", "content": system_message}]
+def compute_perplexity(message):
+    # 制备消息列表，这里只有用户消息
+    messages = [{"role": "user", "content": message}]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
+    # 通过客户端完成聊天生成任务
+    response = client.chat_completion(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
+        max_tokens=512,
+        stream=False,
+        temperature=0.7,
+        top_p=0.95
+    )
+    
+    # 获取生成的文本内容
+    generated_text = response.choices[0].delta.content
 
     # 计算困惑度
-    perplexity_results = perplexity.compute(model_id='gpt2', add_start_token=False, predictions=[response])
+    perplexity_results = perplexity.compute(model_id='gpt2', add_start_token=False, predictions=[generated_text])
     perplexity_value = perplexity_results['perplexity']
-    
-    # 将困惑度结果添加到聊天回复中
-    yield f"Perplexity of the response: {perplexity_value}"
-
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)"
-        ),
-    ]
+
+    # 返回困惑度结果
+    return f"Perplexity of the response: {perplexity_value}"
+
+# 设置 Gradio 界面
+demo = gr.Interface(
+    fn=compute_perplexity,
+    inputs="text",
+    outputs="text",
+    title="Compute Perplexity",
+    description="Enter a text to compute its perplexity based on the gpt2 model."
 )
 
 if __name__ == "__main__":