Update app.py

app.py

@@ -33,12 +33,11 @@ def predict(message, history):
       temperature=0.5,
       repetition_penalty=1.2,
       max_new_tokens=256,
-      streamer=streamer,
       eos_token_id=tokenizer.eos_token_id,
       pad_token_id=tokenizer.eos_token_id
   )
     
-    outputs = model.generate(**inputs, generation_config=generation_config)
+    outputs = model.generate(**inputs,streamer=streamer, generation_config=generation_config)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response