Update app.py

app.py

@@ -90,9 +90,9 @@ def inference(query):
 
     tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
     outputs = model.generate(tokenized_chat, **generation_params)
-    decoded_outputs = tokenizer.batch_decode(outputs, skip_special_tokens=False)
+    # 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 = outputs[0][tokenized_chat.shape[-1]:]
     response = tokenizer.decode(response, skip_special_tokens=True)
     return response
     # outputs = model.generate(tokenized_chat, **generation_params, streamer=streamer)