Update app.py

app.py

@@ -19,7 +19,7 @@ def generate_response(prompt):
     input_ids = inputs["input_ids"].to("cpu")
     print(input_ids)
     # Generate output (ensure it's on CPU)
-    output = model.generate(input_ids, max_length=150, num_return_sequences=1)
+    output = model.generate(input_ids, max_length=150, num_return_sequences=1,pad_token_id=tokenizer.eos_token_id)
     
     # Decode and return response
     response = tokenizer.decode(output[0], skip_special_tokens=True)