Pre-training the embedding models

[panteaHK]

I want to first continue pre-training of bge-en-icl model before fine-tuning it. Could you please refer me to an example of how to do that? I think the examples are no longer in your repo.

[545999961]

You can refer to bge-en-icl finetune

[panteaHK]

I looked at the examples but it's still unclear to me how to set up the fine-tuning to do MLM or Contrastive Learning?

[545999961]

The bge-en-icl model does not require pre-training; it can be directly fine-tuned.