Update README.md

README.md

@@ -45,7 +45,7 @@ if torch.cuda.is_available():
 tokenizer = AutoTokenizer.from_pretrained("zstanjj/SlimPLM-Retrieval-Necessity-Judgment")
 
 # run inference 
-input_ids = tokenizer.encode(question, return_tensors="pt")
+input_ids = tokenizer.encode(prompt.format(question=question, answer=heuristic_answer), return_tensors="pt")
 len_input_ids = len(input_ids[0])
 if torch.cuda.is_available():
     input_ids = input_ids.cuda()