update

app.py

@@ -36,10 +36,10 @@ def respond(
     model_inputs = generate_custom_mask(tokenizer, [prompt], device)
    
     outputs = model.generate(temperature=0.7, max_tokens=32, **model_inputs)
-    # outputs = outputs[:, model_inputs['input_ids'].shape[1]:]
+    outputs = outputs[:, model_inputs['input_ids'].shape[1]:]
     result = tokenizer.batch_decode(outputs, skip_special_tokens=True)
 
-    return "test"
+    return result
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface