update ReadME.md

README.md

@@ -57,7 +57,7 @@ To ensure the consistency of model evaluation, we use [OpenCompass](https://open
 ```python
 >>> from transformers import AutoModelForCausalLM, AutoTokenizer
 >>> tokenizer = AutoTokenizer.from_pretrained("vivo-ai/BlueLM-7B-Base", trust_remote_code=True, use_fast=False)
->>> model = AutoModelForCausalLM.from_pretrained("vivo-ai/BlueLM-7B-Base", device_map="cuda:0", trust_remote_code=True)
+>>> model = AutoModelForCausalLM.from_pretrained("vivo-ai/BlueLM-7B-Base", device_map="cuda:0", torch_dtype=torch.bfloat16, trust_remote_code=True)
 >>> model = model.eval()
 >>> inputs = tokenizer("儒林外史->吴敬梓\n隋唐演义->褚人获\n红楼梦->", return_tensors="pt")
 >>> inputs = inputs.to("cuda:0")
@@ -72,8 +72,8 @@ To ensure the consistency of model evaluation, we use [OpenCompass](https://open
 聊斋志异->蒲松龄
 封神演义->许仲琳
 东周列国志->冯梦龙
-三侠五义->石玉昆
-七剑十三侠->唐芸洲
+三言二拍->冯梦龙
+官场现形记->李宝嘉
 ```
 
 更多使用说明，请参考我们的 [Github 仓库](https://github.com/vivo-ai-lab/BlueLM)。