Update app.py

app.py

@@ -22,8 +22,10 @@ def generate_response(query):
     ]
 
     inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+    print("raw intput: " + inputs)
     outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
-    result = tokenizer.decode(outputs, skip_special_tokens=True)
+    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    print("raw output: " + result)
     return result
 
 # Gradio interface