Skip to content

ModelScope Documentation Update - 2026-04-09 13:21 #221

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
github-actions wants to merge 1 commit into
base: main
Choose a base branch
from
Open

ModelScope Documentation Update - 2026-04-09 13:21 #221

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions docs/flagrelease_en/model_readmes/FlagRelease_GLM-5-FP8-FlagOS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ Environment Setup

### Download FlagOS Image
```bash
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-release-model_glm-5-fp8-tree_0.4.1_3.5-gems_4.2.1rc0-scale_none-cx_none-python_3.12.3-torch_2.9.0-pcp_cuda13.1-gpu_nvidia003-arc_amd64-driver_570.158.01:202604021459
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-release-model_glm-5-fp8-tree_0.4.1_3.5-gems_4.2.1rc0-scale_none-cx_none-python_3.12.3-torch_2.9.0-pcp_cuda13.1-gpu_nvidia003-arc_amd64-driver_570.158.01:20260407170936
```

### Download Open-source Model Weights
Expand All @@ -37,7 +37,7 @@ modelscope download --model FlagRelease/GLM-5-FP8-FlagOS --local_dir /data/GLM-5

### Start the Container
```bash
docker run --rm --init --detach --net=host --uts=host --ipc=host --security-opt=seccomp=unconfined --privileged=true --ulimit stack=67108864 --ulimit memlock=-1 --ulimit nofile=1048576:1048576 --shm-size=32G -v /data:/data --gpus all --name flagos harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-release-model_glm-5-fp8-tree_0.4.1_3.5-gems_4.2.1rc0-scale_none-cx_none-python_3.12.3-torch_2.9.0-pcp_cuda13.1-gpu_nvidia003-arc_amd64-driver_570.158.01:202604021459 sleep infinity
docker run --rm --init --detach --net=host --uts=host --ipc=host --security-opt=seccomp=unconfined --privileged=true --ulimit stack=67108864 --ulimit memlock=-1 --ulimit nofile=1048576:1048576 --shm-size=32G -v /data:/data --gpus all --name flagos harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-release-model_glm-5-fp8-tree_0.4.1_3.5-gems_4.2.1rc0-scale_none-cx_none-python_3.12.3-torch_2.9.0-pcp_cuda13.1-gpu_nvidia003-arc_amd64-driver_570.158.01:20260407170936 sleep infinity
docker exec -it flagos /bin/bash
```
### Start the Server
Expand Down Expand Up @@ -116,4 +116,4 @@ We warmly welcome global developers to join us:
3. Improve technical documentation
4. Expand hardware adaptation support
# License
本模型的权重来源于ZhipuAI/GLM-5-FP8，以apache2.0协议开源: https://www.apache.org/licenses/LICENSE-2.0.txt。
本模型的权重来源于ZhipuAI/GLM-5-FP8，以apache2.0协议开源: https://www.apache.org/licenses/LICENSE-2.0.txt。
4 changes: 2 additions & 2 deletions docs/flagrelease_en/model_readmes/FlagRelease_Qwen3-8B-iluvatar-FlagOS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ vllm-plugin-fl is a vLLM plugin built on the FlagOS unified multi-chip backend,
### Download FlagOS Image

```bash
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-iluvatar-release-model_qwen3-8b-tree_none-gems_4.2.1rc0-scale_0.8.0-cx_none-python_3.10.18-torch_2.7.1_corex.4.4.0-pcp_ix-ml4.4.0-gpu_iluvatar001-arc_amd64-driver_4.4.0:260227
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-iluvatar-release-model_qwen3-8b-tree_none-gems_4.2.1rc0-scale_0.8.0-cx_none-python_3.10.18-torch_2.7.1_corex.4.4.0-pcp_ix-ml4.4.0-gpu_iluvatar001-arc_amd64-driver_4.4.0:202603182010
```

### Download Open-source Model Weights
Expand All @@ -61,7 +61,7 @@ modelscope download --model Qwen/Qwen3-8B --local_dir /nfs/Qwen3-8B

```bash
#Container Startup
docker run --shm-size 128g -dit --name flagos -v /nfs:/root/data -e USE_FLAGGEMS=1 -e QWEN3_PORT=8000 -e QWEN3_PATH=/root/data/Qwen3-8B --privileged --cap-add=ALL --pid=host --net=host harbor.baai.ac.cn/flagrelease-public/flagrelease-iluvatar-release-model_qwen3-8b-tree_none-gems_4.2.1rc0-scale_0.8.0-cx_none-python_3.10.18-torch_2.7.1_corex.4.4.0-pcp_ix-ml4.4.0-gpu_iluvatar001-arc_amd64-driver_4.4.0:260227
docker run --shm-size 128g -dit --name flagos -v /nfs:/root/data -e USE_FLAGGEMS=1 -e QWEN3_PORT=8000 -e QWEN3_PATH=/root/data/Qwen3-8B --privileged --cap-add=ALL --pid=host --net=host harbor.baai.ac.cn/flagrelease-public/flagrelease-iluvatar-release-model_qwen3-8b-tree_none-gems_4.2.1rc0-scale_0.8.0-cx_none-python_3.10.18-torch_2.7.1_corex.4.4.0-pcp_ix-ml4.4.0-gpu_iluvatar001-arc_amd64-driver_4.4.0:202603182010
```

### Serve
Expand Down
4 changes: 2 additions & 2 deletions docs/flagrelease_en/model_readmes/FlagRelease_Qwen3.5-397B-A17B-metax-FlagOS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ This model requires two machines (node1 and node2) on Metax C550. Please execute
### Download FlagOS Image

```bash
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-metax-release-model_qwen3.5-397b-a17b-tree_none-gems_4.2.0-scale_none-cx_0.8.0-python_3.12.11-torch_2.8.0_metax3.3.0.2-pcp_maca3.3.0.15-gpu_metax001-arc_amd64-driver_3.3.12:2602191455
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-metax-release-model_qwen3.5-397b-a17b-tree_none-gems_4.2.0-scale_none-cx_0.8.0-python_3.12.11-torch_2.8.0_metax3.3.0.2-pcp_maca3.3.0.15-gpu_metax001-arc_amd64-driver_3.3.12:202604071102
```

### Download Open-source Model Weights
Expand Down Expand Up @@ -66,7 +66,7 @@ docker run -itd \
--device=/dev/infiniband \
-v /usr/local/:/usr/local/ \
-v /data/:/data/ \
harbor.baai.ac.cn/flagrelease-public/flagrelease-metax-release-model_qwen3.5-397b-a17b-tree_none-gems_4.2.0-scale_none-cx_0.8.0-python_3.12.11-torch_2.8.0_metax3.3.0.2-pcp_maca3.3.0.15-gpu_metax001-arc_amd64-driver_3.3.12:2602191455 \
harbor.baai.ac.cn/flagrelease-public/flagrelease-metax-release-model_qwen3.5-397b-a17b-tree_none-gems_4.2.0-scale_none-cx_0.8.0-python_3.12.11-torch_2.8.0_metax3.3.0.2-pcp_maca3.3.0.15-gpu_metax001-arc_amd64-driver_3.3.12:202604071102 \
/bin/bash

docker exec -it flagos /bin/bash
Expand Down
5 changes: 2 additions & 3 deletions docs/flagrelease_en/model_readmes/FlagRelease_Qwen3.5-397B-A17B-zhenwu-FlagOS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,7 @@ Environment Setup

## Operation Steps

This model requires 2 machines. Please follow this link to apply for 2 machine resources. The platform will configure a 2-machine environment by default, and you only need to execute the subsequent service-related commands.

This model requires 1 machine with 16 GPUs. Please follow this link to apply for 1 machine resource.
link：https://help.aliyun.com/zh/pai/user-guide

### Download FlagOS Image
Expand All @@ -50,7 +49,7 @@ For detailed instructions on how to use this image, please contact the PAI platf


```bash
docker pull baai-cp-registry-vpc.cn-wulanchabu.cr.aliyuncs.com/flagos/flagos:vllm-qwen3-next260219
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-pp-release-model_qwen3.5-397b-a17b-tree_none-gems_5.0.1rc0-scale_none-cx_none-python_3.12.3-torch_2.9.0-pcp_hggc13.0-gpu_pp001-arc_amd64-driver_1.22:202603182010
```

### Download Open-source Model Weights
Expand Down