HF model

tohoku-nlp / bert-large-japanese-v2

Japanese‑BERT‑Large trained on CC‑100 and Wikipedia, using Unidic‑lite word‑level tokenization with WordPiece subwords and whole‑word masking (24 layers, 1024‑dim hidden, 16 heads, 32k vocab), with pretraining code on cl‑tohoku/bert‑japanese.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
66,000
Hugging Face likes
14
Listed
May 13, 2024

Downloads (30-day window) over time

65k70k75k80kNovSepJulMayMarJan 202666,000
Show as a table
MonthDL (30d)
Dec 202569,000
Jan 202668,000
Feb 202665,000
Mar 202665,000
Apr 202668,000
May 202672,000
Jun 202668,000
Jul 202669,000
Aug 202680,000
Sep 202669,000
Oct 202665,000
Nov 202666,000

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