cardiffnlp / text-classification Open weights updated 3 years ago

twitter-xlm-roberta-base-sentiment

Name: twitter-xlm-roberta-base-sentiment
Author: cardiffnlp

This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages (see paper for details).

Params

—

Context

512

Downloads 30d

613 K

Likes

281

Licence: unknown Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 90 K in the last 30 days (12.8%)

1.2 M613 K

Jul 28Sep 1Oct 6Nov 10

Specifications

Architecture: XLMRobertaForSequenceClassification
Context length: 512
Vocabulary: 250,002
Layers / heads: 12 / 12
First seen on the Hub: 2022-03-02
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-classification model

Popular comparisons

bge-reranker-v2-m3 14.8 M roberta-base-go_emotions 4.7 M Bangla-twoclass-Sentiment-Analyzer 3.4 M finbert 3.3 M distilbert-base-uncased-finetuned-sst-2-english 2.9 M twitter-roberta-base-sentiment-latest 2.4 M