Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel
 import torch
 
@@ -29,7 +29,6 @@ def generate_response(user_input, chat_history):
         enable_thinking=True,
     )
 
-    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True)
     inputs = tokenizer(text, return_tensors="pt").to("cpu")
 
     model.generate(
@@ -38,14 +37,10 @@ def generate_response(user_input, chat_history):
         temperature=0.6,
         top_p=0.95,
         top_k=20,
-        streamer = streamer 
+        do_sample=True 
     )
 
-    #response = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
-    response = ""
-    for new_text in streamer:
-        response += new_text
-        
+    response = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
     response = response.split(user_input)[-1].strip()
 
     chat_history.append({"role": "assistant", "content": response})