HF model

ku-nlp / deberta-v2-base-japanese-char-wwm

A Japanese DeBERTa‑V2 base model pre‑trained on 171 GB of Japanese Wikipedia, CC‑100, and OSCAR text with character‑level tokenization, whole‑word masking, trained for 20 days on 8 A100 GPUs, and ready for downstream fine‑tuning.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
24,000
Hugging Face likes
1
Listed
—
Listed since the page was created

Downloads (30-day window) over time

010k20k30kNovSepJulMayMarJan 202624,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 2026—
Mar 2026—
Apr 20265,000
May 20262,000
Jun 20263,000
Jul 20267,000
Aug 20265,000
Sep 20267,000
Oct 202613,000
Nov 202624,000

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