Update app.py

app.py

@@ -81,7 +81,7 @@ def run_model_on_text(text):
 
   streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
-  generation_kwargs = dict(inputs, streamer=streamer,eos_token_id=terminators, max_new_tokens=1024, do_sample=True, repetition_penalty=1.8,)
+  generation_kwargs = dict(inputs, streamer=streamer,eos_token_id=terminators, max_new_tokens=1024, repetition_penalty=1.8,)
   thread = Thread(target=model.generate, kwargs=generation_kwargs)
   thread.start()