huggingface / huggingface/setfit
[FR] use `MultipleNegativesRankingLoss`
Open
enhancement
- Dominant language
- Jupyter Notebook
- Stars
- 2.8k
- Forks
- 267
- Avg merge
- 36m
- Merged PRs (30d)
- 5
Description
If we have more (or equal number of) classes than batch size it should be possible to use `MultipleNegativesRankingLoss`. This might improve performance.
I would like to get comments about this idea and might provide a PR later.
Does anyone have an opinion on this?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.