google / google/paxml

LoRA support in transformers

Open
#96 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
560
Forks
72
PR merge metrics
No merged PRs in 30d

Description

Hi I went through the praxis.transformers.StackedTransformer layer and I don't see any support for LoRA.

That said I was wondering if there was a way to add a set of new LoRA weights to an already existing paxConfig model. If you could give any example that would be great. The tutorials don't cover any such use case where we can update the model layers later.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.