diff --git a/.github/workflows/lint_check.yaml b/.github/workflows/lint_check.yaml
index 678660e..688fadd 100644
--- a/.github/workflows/lint_check.yaml
+++ b/.github/workflows/lint_check.yaml
@@ -12,31 +12,30 @@ jobs:
   lint-check:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
 
-    - name: lint-flake8
-      run: |
-        pip install flake8==v3.8.4
-        FLAKE_DISABLE_LIST="F403,F405,W504,W503,E203"
-        flake8 --max-line-length=120 --ignore=$FLAKE_DISABLE_LIST ./internlm/*
-        flake8 --max-line-length=120 --ignore=$FLAKE_DISABLE_LIST ./train.py
+      - name: lint-flake8
+        run: |
+          pip install flake8==v3.8.4
+          FLAKE_DISABLE_LIST="F403,F405,W504,W503,E203"
+          flake8 --max-line-length=120 --ignore=$FLAKE_DISABLE_LIST ./internlm/*
+          flake8 --max-line-length=120 --ignore=$FLAKE_DISABLE_LIST ./train.py
 
-    - name: lint-isort
-      run: |
-        pip install isort==5.12.0
-        isort --check --profile=black ./internlm/*
-        isort --check --profile=black ./train.py
+      - name: lint-isort
+        run: |
+          pip install isort==5.12.0
+          isort --check --profile=black .
 
-    - name: lint-black
-      run: |
-        pip install black==22.8.0
-        BLACK_EXCLUDE_SETTINGS='\.venv/|\.local/|\.cache/|\.git/'
-        black --line-length=120 --check --exclude $BLACK_EXCLUDE_SETTINGS ./internlm/*
-        black --line-length=120 --check --exclude $BLACK_EXCLUDE_SETTINGS ./train.py
+      - name: lint-black
+        run: |
+          pip install black==22.8.0
+          BLACK_EXCLUDE_SETTINGS='\.venv/|\.local/|\.cache/|\.git/'
+          black --line-length=120 --check --exclude $BLACK_EXCLUDE_SETTINGS ./internlm/*
+          black --line-length=120 --check --exclude $BLACK_EXCLUDE_SETTINGS ./train.py
 
-    - name: lint-pylint
-      run: |
-        pip install pylint==v2.17.2
-        PYLINT_DISABLE_LIST="C0114,C0415,W0212,W0235,W0238,W0621,C0103,R1735,C2801,E0402,C0412,W0719,R1728,W1514,W0718,W0105,W0707,C0209,W0703,W1203"
-        pylint --rcfile .pylintrc --disable=$PYLINT_DISABLE_LIST ./internlm/*
-        pylint --rcfile .pylintrc --disable=$PYLINT_DISABLE_LIST ./train.py
+      - name: lint-pylint
+        run: |
+          pip install pylint==v2.17.2
+          PYLINT_DISABLE_LIST="C0114,C0415,W0212,W0235,W0238,W0621,C0103,R1735,C2801,E0402,C0412,W0719,R1728,W1514,W0718,W0105,W0707,C0209,W0703,W1203"
+          pylint --rcfile .pylintrc --disable=$PYLINT_DISABLE_LIST ./internlm/*
+          pylint --rcfile .pylintrc --disable=$PYLINT_DISABLE_LIST ./train.py
diff --git a/README.md b/README.md
index 22a610c..a26d8de 100644
--- a/README.md
+++ b/README.md
@@ -26,7 +26,7 @@
 [🤔Reporting Issues](https://github.com/InternLM/InternLM/issues/new)
 
 [English](./README.md) |
-[简体中文](./README_zh-CN.md) |
+[简体中文](./README_zh-CN.md)
 
 </div>
 
diff --git a/README_zh-CN.md b/README_zh-CN.md
index e4a460b..24b8030 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -27,7 +27,7 @@
 [🤔提交反馈](https://github.com/InternLM/InternLM/issues/new)
 
 [English](./README.md) |
-[简体中文](./README_zh-CN.md) |
+[简体中文](./README_zh-CN.md)
 
 </div>
 
diff --git a/chat/README.md b/chat/README.md
index ee19878..48a953b 100644
--- a/chat/README.md
+++ b/chat/README.md
@@ -1,6 +1,6 @@
 # Chat
 
-English | [简体中文](lmdeploy_zh_zh-CN.md)
+English | [简体中文](./README_zh-CN.md)
 
 This document briefly shows how to use [Transformers](#import-from-transformers), [ModelScope](#import-from-modelscope), and [Web demos](#dialogue) to conduct inference with InternLM2-Chat.
 
diff --git a/chat/README_zh-CN.md b/chat/README_zh-CN.md
index 5f8491b..613de60 100644
--- a/chat/README_zh-CN.md
+++ b/chat/README_zh-CN.md
@@ -1,6 +1,6 @@
 # 对话
 
-[English](lmdeploy.md) | 简体中文
+[English](./README.md) | 简体中文
 
 本文介绍采用 [Transformers](#import-from-transformers)、[ModelScope](#import-from-modelscope)、[Web demos](#dialogue)
 对 InternLM2-Chat 进行推理。
diff --git a/chat/web_demo.py b/chat/web_demo.py
index 2ddee4e..a5c160a 100644
--- a/chat/web_demo.py
+++ b/chat/web_demo.py
@@ -26,11 +26,11 @@ def on_btn_click():
 @st.cache_resource
 def load_model():
     model = (
-        AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
+        AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True)
         .to(torch.bfloat16)
         .cuda()
     )
-    tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
+    tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-7b", trust_remote_code=True)
     return model, tokenizer
 
 
@@ -46,9 +46,9 @@ def prepare_generation_config():
     return generation_config
 
 
-user_prompt = "<|User|>:{user}\n"
-robot_prompt = "<|Bot|>:{robot}<eoa>\n"
-cur_query_prompt = "<|User|>:{user}<eoh>\n<|Bot|>:"
+user_prompt = "[UNUSED_TOKEN_146]user\n{user}[UNUSED_TOKEN_145]\n"
+robot_prompt = "[UNUSED_TOKEN_146]assistant\n{robot}[UNUSED_TOKEN_145]\n"
+cur_query_prompt = "[UNUSED_TOKEN_146]user\n{user}[UNUSED_TOKEN_145]\n[UNUSED_TOKEN_146]assistant\n"
 
 
 def combine_history(prompt):
@@ -73,10 +73,10 @@ def main():
     model, tokenizer = load_model()
     print("load model end.")
 
-    user_avator = "docs/imgs/user.png"
-    robot_avator = "docs/imgs/robot.png"
+    user_avator = "assets/user.png"
+    robot_avator = "assets/robot.png"
 
-    st.title("InternLM-Chat-7B")
+    st.title("InternLM2-Chat-7B")
 
     generation_config = prepare_generation_config()