Update app.py

app.py

@@ -84,8 +84,6 @@ def evaluate(
     top_k=40,
     num_beams=4,
     max_new_tokens=128,
-    print('instruction: ', instruction)
-    return instruction
     prompt = instruction
     inputs = tokenizer(prompt, return_tensors="pt")
     input_ids = inputs["input_ids"].to(device)
@@ -106,7 +104,7 @@ def evaluate(
         )
     s = generation_output.sequences[0]
     output = tokenizer.decode(s)
-    return output.split("### Response:")[1].strip()
+    return output[len(input_ids):]
 
 
 g = gr.Interface(