diff --git a/README-zh-Hans.md b/README-zh-Hans.md
index c374344..2281d7d 100644
--- a/README-zh-Hans.md
+++ b/README-zh-Hans.md
@@ -86,7 +86,7 @@ InternLM ，即书生·浦语大模型，包含面向实用场景的70亿参数
 ```python
 >>> from transformers import AutoTokenizer, AutoModelForCausalLM
 >>> tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
->>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", torch_dtype=torch.float16, trust_remote_code=True).cuda()
+>>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).cuda()
 >>> model = model.eval()
 >>> response, history = model.chat(tokenizer, "你好", history=[])
 >>> print(response)
diff --git a/README.md b/README.md
index f1fa219..c66a0ae 100644
--- a/README.md
+++ b/README.md
@@ -90,7 +90,7 @@ To load the InternLM 7B Chat model using Transformers, use the following code:
 ```python
 >>> from transformers import AutoTokenizer, AutoModelForCausalLM
 >>> tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
->>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", torch_dtype=torch.float16, trust_remote_code=True).cuda()
+>>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).cuda()
 >>> model = model.eval()
 >>> response, history = model.chat(tokenizer, "hello", history=[])
 >>> print(response)