HF model

tohoku-nlp / bert-base-japanese-whole-word-masking

Japanese BERT‑base pretrained on 2019 Japanese Wikipedia with IPA‑dictionary and whole‑word masking, 12‑layer 768‑dim, 32,000‑vocab, 512‑token sequences, 1 M steps, available at cl‑tohoku/bert‑japanese under CC‑BY‑SA.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
462,000
Hugging Face likes
76
Listed
May 13, 2024

Downloads (30-day window) over time

300k400k500kNovSepJulMayMarJan 2026462,000
Show as a table
MonthDL (30d)
Dec 2025364,000
Jan 2026500,000
Feb 2026495,000
Mar 2026409,000
Apr 2026305,000
May 2026354,000
Jun 2026387,000
Jul 2026388,000
Aug 2026352,000
Sep 2026334,000
Oct 2026392,000
Nov 2026462,000

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