facebookresearch/fairseq
Ver no GitHubPython API Transformer.from_pretrained support directly to load on GPU
Open
#2.480 aberto em 13 de ago. de 2020
enhancementhelp wanted
Métricas do repositório
- Stars
- (29.107 stars)
- Métricas de merge de PR
- (Nenhuma PRs mesclada em 30d)
Description
❓ Questions and Help
Hi,
I'm using the API command to load my finetuned mBART model, below is the command:
en2ar = TransformerModel.from_pretrained(
'/home/ubuntu/mayub/models',
checkpoint_file='checkpoint_best_en-ar_ft.pt',
data_name_or_path='/home/ubuntu/mayub/models',
bpe='sentencepiece',
sentencepiece_vocab='sentencepiece.bpe.model'
)
Looks like this loads the model first on cpu and then I do en2ar.cuda() to replicate again on GPU device.

Is there a way I can avoid the loading on both devices and just directly load on GPU. Reason is I have 5 other models which I need to load and save on RAM.
Appreciate any help. Thanks !