facebookresearch / facebookresearch/sam2
Plans for Parameter Efficient Fine Tuning (PEFT)?
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
For instance, adding LoRA to image encoder? Here is a [repository](https://github.com/25benjaminli/sam2lora) that I made that attempts to use LoRA on the attention in the image encoder although I didn't find significant performance gains. Would appreciate feedback regarding the validity of the approach.
Contributor guide
Assessment
This issue has not been assessed yet.