HF model

ku-nlp / deberta-v2-tiny-japanese

Japanese DeBERTa V2 tiny, pretrained on ~171 GB of Japanese Wikipedia, CC‑100, and OSCAR corpora, requires Juman++ word segmentation, was trained in 33 h on 8 NVIDIA A100 GPUs, and can be fine‑tuned for downstream tasks.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
14,000
Hugging Face likes
5
Listed
—
Listed since the page was created

Downloads (30-day window) over time

010k20kNovSepJulMayMarJan 202614,000
Show as a table
MonthDL (30d)
Dec 20257,000
Jan 20263,000
Feb 20262,000
Mar 20267,000
Apr 20267,000
May 20269,000
Jun 20263,000
Jul 202611,000
Aug 20265,000
Sep 202619,000
Oct 202612,000
Nov 202614,000

Downloads over the 30 days before the last snapshot of each month.

Popular in the same category

Resources in similar research fields

Learn from slides & articles