Update README.md

README.md

@@ -53,7 +53,7 @@ tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
 text = "There is a girl who likes adventure,"
 inputs = tokenizer(text, return_tensors="pt", return_attention_mask=False).to(model.device)
-outputs = model.generate(**inputs, max_length=50)
+outputs = model.generate(**inputs, max_new_tokens=50)
 text = tokenizer.batch_decode(outputs)[0]
 ```