Update app.py

app.py

@@ -125,7 +125,7 @@ def bot(history,message):
 	"""
 	Prints the LLM's response in the chatbot
 	"""
-	response = bot_response(message)
+	response = "That's great!!!"#bot_response(message)
 	history[-1][1] = ""
 	for character in response:
 		history[-1][1] += character
@@ -135,7 +135,7 @@ def bot(history,message):
 def bot_response(message):
 	"""
 	Generates a response from the LLM model.
-	max_new_tokens, temperature and top_p are set to 512, 0.6 and 0.9 respectively.
+	max_new_tokens, temperature and top_p are set to 256, 0.6 and 0.9 respectively.
 	"""
 	messages = [
     {"role": "system", "content": "You are a helpful AI assistant."},
@@ -155,13 +155,12 @@ def bot_response(message):
 
 	outputs = pipeline(
 		prompt,
-		max_new_tokens=512,
+		max_new_tokens=256,
 		eos_token_id=terminators,
 		do_sample=True,
 		temperature=0.6,
 		top_p=0.9,
 	)
-	print(outputs[0]["generated_text"][len(prompt):])
 	return outputs[0]["generated_text"][len(prompt):]
 
 with gr.Blocks(