bobox
/

DeBERTa-ST-AllLayers-v3.1

Sentence Similarity

sentence-transformers

feature-extraction

Generated from Trainer

dataset_size:203905

loss:AdaptiveLayerLoss

loss:CoSENTLoss

loss:GISTEmbedLoss

loss:OnlineContrastiveLoss

loss:MultipleNegativesSymmetricRankingLoss

loss:MultipleNegativesRankingLoss

Inference Endpoints

Model card Files Files and versions Community

DeBERTa-ST-AllLayers-v3.1 / added_tokens.json

bobox's picture

KL divergence loss layers selfdistill....Multi step multi task training.

a232ba1 verified about 23 hours ago

No virus

23 Bytes

	{
	"[MASK]": 128000
	}