Update model.py

model.py

@@ -13,7 +13,7 @@ os.system('pip install "unsloth[colab-new] @ git+https://github.com/unslothai/un
 
 import gradio as gr
 
-from transformers import TextStreamer
+# from transformers import TextStreamer
 from unsloth import FastLanguageModel
 from google.colab import drive
 
@@ -52,10 +52,10 @@ def chat_alpaca(message: str, history: list, temperature: float, max_new_tokens:
     inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
 
     # Define the streamer
-    text_streamer = TextStreamer(tokenizer)
+    # text_streamer = TextStreamer(tokenizer)
 
     # Generate the response
-    outputs = model.generate(**inputs, streamer=text_streamer, max_new_tokens=max_new_tokens, temperature=temperature)
+    outputs = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature=temperature)
     response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
 
     # Return the response