update README.md

README.md

@@ -34,7 +34,7 @@ messages = [
 input_ids = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors='pt')
 if torch.cuda.is_available():
     input_ids = input_ids.to('cuda')
-pred = model.generate(**inputs, max_new_tokens=512, repetition_penalty=1.06, eos_token_id=tokenizer.eos_token_id)
+pred = model.generate(input_ids, max_new_tokens=512, repetition_penalty=1.06, eos_token_id=tokenizer.eos_token_id)
 print(tokenizer.decode(pred[0][input_ids.shape[1]:], skip_special_tokens=True))
 ```