diff --git a/.github/workflows/demo_in_readme.yaml b/.github/workflows/demo_in_readme.yaml
deleted file mode 100644
index 70c35ea..0000000
--- a/.github/workflows/demo_in_readme.yaml
+++ /dev/null
@@ -1,128 +0,0 @@
-name: demo-in-readme
-on:
-  pull_request:
-    branches:
-      - "main"
-      - "develop"
-    paths-ignore:
-      - "docs/**"
-      - "**.md"
-env:
-  WORKSPACE_PREFIX: $(echo $GITHUB_WORKSPACE |cut -d '/' -f 1-4)
-  SLURM_PARTITION: llm_s
-
-jobs:
-  check-requirements:
-    runs-on: [t_cluster]
-    steps:
-    - name: mask env
-      run: |
-        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
-    - uses: actions/checkout@v3
-      with:
-         fetch-depth: 2
-    - name: check-requirements
-      run: |
-        source activate internlm-env-test
-        changed_files=$(git diff --name-only -r HEAD^1 HEAD)
-        echo $changed_files
-        if [[ $changed_files =~ "runtime.txt" ]]; then
-          pip install -r requirements/runtime.txt
-        fi
-
-        if [[ $changed_files =~ "torch.txt"  ]]; then
-          pip install -r requirements/torch.txt
-        fi
-
-  dataset-preparation:
-    if: ${{ always() }}
-    needs: check-requirements
-    runs-on: [t_cluster]
-    steps:
-    - name: mask env
-      run: |
-        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
-    - uses: actions/checkout@v3
-
-    - name: raw-chinese-data
-      run: |
-        source activate internlm-env-test
-        sh ./ci_scripts/data/tokenizer_chinese.sh ${GITHUB_RUN_ID}-${GITHUB_JOB}
-
-    - name: alpaca-data
-      run: |
-        source activate internlm-env-test
-        sh ./ci_scripts/data/tokenizer_alpaca.sh
-
-  train:
-    if: ${{ always() }}
-    needs: check-requirements
-    runs-on: [t_cluster]
-    timeout-minutes: 30
-    steps:
-    - name: mask env
-      run: |
-        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
-    - uses: actions/checkout@v3
-
-    - name: slurm-train
-      id: basic_train
-      run: |
-        source activate internlm-env-test
-        sh ./ci_scripts/train/slurm_train.sh ${GITHUB_RUN_ID}-${GITHUB_JOB}
-
-    - name: load_preset_ckpt
-      if: ${{ failure() && steps.basic_train.conclusion == 'failure' }}
-      run: |
-        source activate internlm-env-test
-        export PYTHONPATH=$PWD:$PYTHONPATH
-        sh ./ci_scripts/train/load_ckpt.sh 7B_load_preset_ckpt ${GITHUB_RUN_ID}-${GITHUB_JOB}
-
-    - name: load_new_ckpt
-      run: |
-        source activate internlm-env-test
-        export PYTHONPATH=$PWD:$PYTHONPATH
-        sh ./ci_scripts/train/load_ckpt.sh 7B_load_new_ckpt ${GITHUB_RUN_ID}-${GITHUB_JOB}
-        rsync -av --remove-source-files $GITHUB_WORKSPACE/llm_ckpts ${{env.WORKSPACE_PREFIX}}/ci_clean_bak
-
-    - name: torchrun-train
-      run: |
-        source activate internlm-env-test
-        sh ./ci_scripts/train/torchrun.sh ${GITHUB_RUN_ID}-${GITHUB_JOB}
-        rsync -av --remove-source-files $GITHUB_WORKSPACE/llm_ckpts ${{env.WORKSPACE_PREFIX}}/ci_clean_bak
-
-  convert-model-then-load:
-    if: ${{ always() }}
-    needs: check-requirements
-    runs-on: [t_cluster]
-    timeout-minutes: 15
-    steps:
-    - name: mask env
-      run: |
-        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
-    - uses: actions/checkout@v3
-
-    - name: convert-model-then-load
-      run: |
-        source activate internlm-env-test
-        export PYTHONPATH=$PWD:$PYTHONPATH
-        sh ./ci_scripts/model/convert_to_hf.sh
-        cd ./hf_ckpt
-        srun -p ${SLURM_PARTITION} --quotatype=spot --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 python ../ci_scripts/model/loaded_as_transformer.py
-        cd ..
-        rsync -av --remove-source-files $GITHUB_WORKSPACE/hf_ckpt ${{env.WORKSPACE_PREFIX}}/ci_clean_bak
-  load-chat-model-in-hf:
-    if: ${{ always() }}
-    needs: check-requirements
-    runs-on: [t_cluster]
-    timeout-minutes: 15
-    steps:
-    - name: mask env
-      run: |
-        echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
-    - uses: actions/checkout@v3
-
-    - name: chat-model-in-hf
-      run: |
-        source activate internlm-env-test
-        srun -p ${SLURM_PARTITION} --quotatype=spot --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 python ./ci_scripts/model/demo_load_7B_chat_model.py