Update app.py

app.py

@@ -93,7 +93,7 @@ def inference(query):
     decoded_outputs = tokenizer.batch_decode(outputs, skip_special_tokens=False)
     # assistant_response = decoded_outputs[0].split("<|start_header_id|>assistant<|end_header_id|>")[-1].strip()
     response = decoded_outputs[0][tokenized_chat.shape[-1]:]
-    response = tokenizer.decode(response, skip_special_tokens=True))
+    response = tokenizer.decode(response, skip_special_tokens=True)
     return response
     # outputs = model.generate(tokenized_chat, **generation_params, streamer=streamer)
     # return outputs