关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
thomas-yanxin
/
Qwen
mirror of https://github.com/QwenLM/Qwen.git
Not watched
1
0
Fork 0
Code
Releases 0 Wiki Activity
Issues 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
480 Commits
24 Branches
36 MiB
4 Download
 
 
 
 
 
 
Branch: main
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'main'
${ noResults }
Qwen/ascend-support
yangapku e8e15962d8 add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support 5 months ago
..
README.md add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support 5 months ago
docker_qwen.sh add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support 5 months ago

README.md

昇腾910架构基于mindformers推理Qwen-7B-Chat模型

环境要求

  • 硬件：Ascend 910A/B

运行步骤

首先参考Qwen README下载官方模型到/path/to/Qwen-7B-Chat。

下载并启动镜像

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}

执行权重转换

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。

执行推理

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
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

Markdown Python Jupyter Notebook Shell Text other

Please read the following content carefully:

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》

Agree and continue
Disagree, exit