Update README.md

README.md

@@ -142,9 +142,9 @@ InternLM2 模型具备以下的技术特点
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-1_8b-sft", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-1_8b", trust_remote_code=True)
 # `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，导致显存不足
-model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-1_8b-sft", torch_dtype=torch.float16, trust_remote_code=True).cuda()
+model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-1_8b", torch_dtype=torch.float16, trust_remote_code=True).cuda()
 model = model.eval()
 response, history = model.chat(tokenizer, "你好", history=[])
 print(response)
@@ -159,7 +159,7 @@ print(response)
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_path = "internlm/internlm2-chat-1_8b-sft"
+model_path = "internlm/internlm2-chat-1_8b"
 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dype=torch.float16, trust_remote_code=True).cuda()
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)