fix README

README.md

@@ -64,14 +64,14 @@ We have evaluated InternLM2 on several important benchmarks using the open-sourc
 
 ### Import from Transformers
 
-To load the InternLM2 1.8B Chat SFT model using Transformers, use the following code:
+To load the InternLM2 1.8B Chat model using Transformers, use the following code:
 
 ```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)
 # Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and cause OOM Error.
-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, "hello", history=[])
 print(response)
@@ -86,7 +86,7 @@ The responses can be streamed using `stream_chat`:
 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_dtype=torch.float16, trust_remote_code=True).cuda()
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
 
@@ -106,7 +106,7 @@ The code is licensed under Apache-2.0, while model weights are fully open for ac
 
 - InternLM2-1.8B: 具有高质量和高适应灵活性的基础模型，为下游深度适应提供了良好的起点。
 - InternLM2-Chat-1.8B-SFT：在 InternLM2-1.8B 上进行监督微调 (SFT) 后得到的对话模型。
-- InternLM2-chat-1.8B：通过在线 RLHF 在 InternLM2-Chat-1.8B-SFT 之上进一步对齐。 InternLM2-Chat-1.8B 表现出更好的指令跟随、聊天体验和函数调用，推荐下游应用程序使用。
+- InternLM2-Chat-1.8B：通过在线 RLHF 在 InternLM2-Chat-1.8B-SFT 之上进一步对齐。 InternLM2-Chat-1.8B表现出更好的指令跟随、聊天体验和函数调用，推荐下游应用程序使用。
 
 InternLM2 模型具备以下的技术特点
 
@@ -137,7 +137,7 @@ InternLM2 模型具备以下的技术特点
 
 ### 通过 Transformers 加载
 
-通过以下的代码加载 InternLM2 1.8B Chat SFT 模型
+通过以下的代码加载 InternLM2 1.8B Chat 模型
 
 ```python
 import torch