Merge pull request #16 from FlagAI-Open/master

update

Author: shunxing1234

.github/workflows/python-app.yml

@@ -1,6 +1,7 @@
 # This workflow will install Python dependencies, run tests and lint with a single version of Python
 # For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
 
+
 name: Python application
 
 on:
@@ -19,10 +20,10 @@ jobs:
 
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python 3.10
+    - name: Set up Python 3.9
       uses: actions/setup-python@v3
       with:
-        python-version: "3.10"
+        python-version: "3.9"
     - name: Install dependencies
       run: |
         python -m pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple

.github/workflows/python-publish.yml

@@ -11,7 +11,7 @@ on:
 
 jobs:
   deploy:
-    runs-on: ubuntu-18.04
+    runs-on: self-hosted
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python
@@ -28,4 +28,4 @@ jobs:
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           user: __token__
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          password: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -19,6 +19,8 @@ test_report
 /data/
 /tests/*/data
 checkpoints
+checkpoints_in
+checkpoints_out
 state_dict
 checkpoints*
 vocabs
@@ -28,3 +30,9 @@ qqp
 glm_large_qqp_pytorch
 wandb
 clip_benchmark_datasets
+examples/AltCLIP/clip_benchmark_datasets
+examples/glm_pretrain/data.lazy
+examples/glm_pretrain/examples/glm_pretrain/data.lazy
+examples/vit_cifar100/cifar100
+examples/vit_cifar100/data
+output/

BAAI_Aquila_Model_License.pdf

@@ -1,53 +1,61 @@
-#Change to your base image, such as pytorch1.11+py38
-#https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel_21-02.html#rel_21-02
-FROM nvcr.io/nvidia/pytorch:21.06-py3
-#You can set available pypi sources
-RUN /bin/bash -c "pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple"
-
-ENV STAGE_DIR=/tmp
-RUN mkdir -p ${STAGE_DIR}
-#Ubuntu
-RUN apt-get update && apt-get install -y openssh-server && apt-get install -y git
-ARG SSH_PORT=6001
-#Client Liveness & Uncomment Port 22 for SSH Daemon
-RUN echo "ClientAliveInterval 30" >> /etc/ssh/sshd_config
-RUN mkdir -p /var/run/sshd && cp /etc/ssh/sshd_config ${STAGE_DIR}/sshd_config && \
-    sed "0,/^#Port 22/s//Port 22/" ${STAGE_DIR}/sshd_config > /etc/ssh/sshd_config
-RUN cat /etc/ssh/sshd_config > ${STAGE_DIR}/sshd_config && \
-    sed "0,/^Port 22/s//Port ${SSH_PORT}/" ${STAGE_DIR}/sshd_config > /etc/ssh/sshd_config && \
-    sed -i 's/#PermitRootLogin prohibit-password/PermitRootLogin yes/g' /etc/ssh/sshd_config
-EXPOSE ${SSH_PORT}
-
-#Set SSH KEY
-RUN mkdir /root/.ssh
-RUN printf "#StrictHostKeyChecking no\n#UserKnownHostsFile /dev/null" >> /etc/ssh/ssh_config && \
- ssh-keygen -t rsa -f /root/.ssh/id_rsa -N "" && cat /root/.ssh/id_rsa.pub >> /root/.ssh/authorized_keys && \
-   chmod og-wx /root/.ssh/authorized_keys
-
-RUN echo $'Host 127.0.0.1 \n\
-    Hostname 127.0.0.1 \n\
-    Port 6001 \n\
-    StrictHostKeyChecking no \n\
-    User root' > /root/.ssh/config
-RUN echo $'Host localhost \n\
-    Hostname localhost \n\
-    Port 6001 \n\
-    StrictHostKeyChecking no \n\
-    User root' >> /root/.ssh/config
-
-RUN echo "service ssh start" >> /root/.bashrc
-
-#Main deps
-RUN pip install tensorboard
-RUN pip install sentencepiece
-RUN pip install boto3
-RUN pip install jieba
-RUN pip install ftfy
-RUN pip install deepspeed==0.7.7
-RUN pip install bmtrain
-
-RUN pip install flagai
-#For development usage, you can change as follows
-#RUN git clone https://github.com/FlagAI-Open/FlagAI.git && cd FlagAI && python setup.py install
+FROM nvcr.io/nvidia/cuda:11.7.0-devel-ubuntu20.04
+
+LABEL zhanglu0704
+
+ENV TZ=Asia/Shanghai
+
+VOLUME /etc/localtime
+
+ENV WORK_DID=/workspace
+
+WORKDIR ${WORK_DID}
+
+RUN apt update && \
+    apt install -y g++ gcc cmake curl wget vim unzip git openssh-server net-tools python3-packaging && \
+    apt install -y python3.9 python3.9-dev python3-pip && \
+    apt clean -y && \
+    rm -rf /var/cache/apt/archives 
+
+RUN rm /usr/bin/python3 && \
+    ln -s /usr/bin/python3.9 /usr/bin/python3 && \
+    ln -s /usr/bin/python3 /usr/bin/python && \
+    python -m pip install --upgrade pip
+
+RUN pip install torch==1.13.0+cu117 torchvision==0.14.0+cu117 torchaudio==0.13.0 \
+    --extra-index-url https://download.pytorch.org/whl/cu117
+
+COPY requirements.txt  ${WORK_DID}/
+
+RUN python -m pip install -r ${WORK_DID}/requirements.txt
+
+RUN git clone https://github.com/NVIDIA/apex && \
+    cd apex && \
+    # git checkout -f 23.05 && \
+    # pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" . && \
+    pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" . && \
+    cd ../ && rm -rf apex
+
+RUN git clone https://github.com/OpenBMB/BMTrain && \
+    cd BMTrain && \
+    git checkout -f 0.2.2 && \
+    # python setup.py install --prefix=/usr/local/
+    pip install -v . && \
+    cd ../ && rm -rf BMTrain
+
+RUN git clone https://github.com/FlagAI-Open/FlagAI.git && \
+    cd FlagAI && \
+    pip install -v . && \
+    cd ../ && rm -rf FlagAI
+
+RUN echo "ClientAliveInterval 30" >> /etc/ssh/sshd_config && \
+    sed -i 's/#PermitRootLogin prohibit-password/PermitRootLogin yes/g' /etc/ssh/sshd_config && \
+    echo "StrictHostKeyChecking no" >> /etc/ssh/ssh_config && \
+    echo "UserKnownHostsFile /dev/null" >> /etc/ssh/ssh_config
+
+RUN ssh-keygen -t rsa -f /root/.ssh/id_rsa -N "" && \
+    cat /root/.ssh/id_rsa.pub >> /root/.ssh/authorized_keys && \
+    chmod og-wx /root/.ssh/authorized_keys
 
 CMD service ssh start && tail -f /dev/null
+
+# sudo docker build -f Dockerfile --shm-size='120g' -t flagai:dev-ubuntu20-cuda11.7-py39 .