Update app.py

app.py

@@ -24,7 +24,9 @@ def generate_response(model, tokenizer, prompt):
         attention_mask=attention_mask,
         pad_token_id=pad_token_id
     )
-    return tokenizer.decode(output[0], skip_special_tokens=True)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = response[len(prompt):]
+    return response
 
 def predict(input):
     prediction = generate_response(my_model, my_tokenizer, input)