Update app.py

app.py

@@ -1,20 +1,14 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import evaluate
 
-"""
-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
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# 创建困惑度计算工具
+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,
-):
+def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -35,13 +29,16 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    # 计算困惑度
+    perplexity_results = perplexity.compute(model_id='gpt2', add_start_token=False, predictions=[response])
+    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=[
@@ -53,11 +50,10 @@ demo = gr.ChatInterface(
             maximum=1.0,
             value=0.95,
             step=0.05,
-            label="Top-p (nucleus sampling)",
+            label="Top-p (nucleus sampling)"
         ),
-    ],
+    ]
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()