Is it possible to support pretrained model with dynamic adapters?

[BrightXiaoHan]

Hi. I want to implement a feature to train a generic translation model on a large dataset, where we have many translator users, each of whom has a personal memory bank they maintain. I would like to use Pretrain Transformer + Adapter Layers to support users to upload some data to finetune customized models. Is it possible for CTranslate2 to support such dynamic loading and releasing of Adapter parameters?

[guillaumekln]

Hi,

Currently this is not possible.

Can you describe a bit more these adapter layers? Is there a public paper or implementation for reference?

[BrightXiaoHan]

Simple, Scalable Adaptation for Neural Machine Translation

adapter-transformers