microsoft / text-classification updated 4 years ago

deberta-xlarge-mnli

Name: deberta-xlarge-mnli
Author: microsoft

DeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training data.

Params

—

Context

512

Downloads 30d

349 K

Likes

Commercial use: allowed mit Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 50 days

▲ 461 K in the last 30 days (56.9%)

818 K218 K

Aug 2Aug 18Sep 4Sep 20

Specifications

Architecture: DebertaForSequenceClassification
Context length: 512
Vocabulary: 50,265
Layers / heads: 48 / 16
Licence: mit
First seen on the Hub: 2022-03-02
Training datasets: undisclosed
Added to our catalog: 2026-08-02

Compare with any text-classification model

Popular comparisons

bge-reranker-v2-m3 17.6 M finbert 5.3 M Prompt-Guard-86M 4.4 M bge-reranker-base 4.0 M distilbert-base-uncased-finetuned-sst-2-english 3.7 M twitter-roberta-base-sentiment-latest 3.2 M