Update app.py

app.py

@@ -9,12 +9,12 @@ client = InferenceClient(
 def format_prompt(message, history):
   prompt = ""
   for user_prompt, bot_response in history:
-    prompt += f"GPT4 Correct User: {user_prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>"
+    prompt += f"GPT4 Correct User: {user_prompt}<|end_of_turn|>GPT4 Correct Assistant: {bot_response}<|end_of_turn|>"
   prompt += f"GPT4 Correct User: {message}<|end_of_turn|>GPT4 Correct Assistant:"
   return prompt
 
 def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.9, max_new_tokens=1024, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -35,6 +35,8 @@ def generate(
     output = ""
 
     for response in stream:
+        if response.token.text=="<|end_of_turn|>":
+            break
         output += response.token.text
         yield output
     return output