fix example prompt

README.md

@@ -130,7 +130,7 @@ tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-20b", trust_remote
 # `torch_dtype=torch.float16` 可以令模型以 float16 精度加载，否则 transformers 会将模型加载为 float32，有可能导致显存不足
 model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-20b", torch_dtype=torch.float16, trust_remote_code=True).cuda()
 model = model.eval()
-inputs = tokenizer(["来到美丽的大自然，我们发现"], return_tensors="pt")
+inputs = tokenizer(["来到美丽的大自然"], return_tensors="pt")
 for k,v in inputs.items():
     inputs[k] = v.cuda()
 gen_kwargs = {"max_length": 128, "top_p": 0.8, "temperature": 0.8, "do_sample": True, "repetition_penalty": 1.0}