Hugging Face's logo

BAAI
/
bge-large-zh-noinstruct

Feature Extraction
Transformers
PyTorch
Chinese
bert
text-embeddings-inference
Model card Files
xet
 Community
4

How this model is allocated to 4 A100GPU use, when called, the video memory is displayed in one graphics card

#3
by jamboom - opened
Discussion
jamboom

How this model is allocated to 4 A100GPU use, when called, the video memory is displayed in one graphics card
Shitao
 Beijing Academy of Artificial Intelligence org

If you use FlagModel, it will use all available GPUs automatically. For transformers, you need to add this command model = torch.nn.DataParallel(model).
For sentence transformers, you can refer to https://github.com/UKPLab/sentence-transformers .

Sign up or log in to comment