TrustSafeAI / text-classification updated 2 years ago

RADAR-Vicuna-7B

Name: RADAR-Vicuna-7B
Author: TrustSafeAI

RADAR-Vicuna-7B is an AI-text detector trained via adversarial learning between the detector and a paraphraser on human-text corpus (OpenWebText) and AI-text corpus generated based on OpenWebText.

Params

7.0 B

Context

512

Downloads 30d

315 K

Likes

Licence: unknown Not gated View on Hugging Face ↗

Download history

daily snapshots · 55 days

▲ 622 K in the last 30 days (66.4%)

1.1 M315 K

Jul 28Aug 15Sep 2Sep 20

Specifications

Architecture: RobertaForSequenceClassification
Parameters: 7.0 B
Context length: 512
Vocabulary: 50,265
Layers / heads: 24 / 16
First seen on the Hub: 2023-06-24
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-classification model

Popular comparisons

bge-reranker-v2-m3 17.6 M finbert 5.3 M twitter-roberta-base-sentiment-latest 3.2 M ms-marco-MiniLM-L-6-v2 1.1 M finbert-tone 1.0 M twitter-xlm-roberta-base-sentiment 943 K