Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yangapku e8e15962d8 | 5 months ago | |
---|---|---|
.. | ||
README.md | 5 months ago | |
docker_qwen.sh | 5 months ago |
首先参考Qwen README下载官方模型到/path/to/Qwen-7B-Chat
。
docker pull qwenllm/qwen-mindspore:latest
cd /path/to/Qwen/ascend-support
# 下载模型到此处
CHECKPOINT_PATH=/path/to/Qwen-7B-Chat
cd ascend-support
# 启动docker容器
bash docker_qwen.sh -c ${CHECKPOINT_PATH}
在容器内执行下面的命令,将Qwen模型转换为适配mindformers
的格式:
python3 /data/qwen/mindformers/research/qwen/convert_weight.py
转换后模型的输出位置为${CHECKPOINT_PATH}/qwen-7b-chat.ckpt
。
在容器内执行下面的命令,进行推理:
cd /data/qwen/mindformers/research/qwen
export PYTHONPATH=/data/qwen/mindformers:$PYTHONPATH
python3 infer_qwen.py
No Description
Markdown Python Jupyter Notebook Shell Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》