add attention mask and pad token id

app.py

@@ -32,7 +32,11 @@ Your output should be in JSON FORMAT with the keys "REASONING" and "SCORE":
 def model_call(question, document, answer):
     NEW_FORMAT = PROMPT.format(question=question, document=document, answer=answer)
     inputs = tokenizer(NEW_FORMAT, return_tensors="pt")
-    model.generate(inputs.input_ids)
+    model.generate(
+        inputs.input_ids,
+        attention_mask=inputs.attention_mask,
+        pad_token_id=tokenizer.eos_token_id,
+    )
     generated_text = tokenizer.decode(inputs.input_ids[0])
     print(generated_text)
     return generated_text