HF model

tohoku-nlp / bert-base-japanese-v3

Japanese BERT‑base (12 layers, 768‑dim hidden, 12 heads, 32 k vocab) pretrained with whole‑word masking on CC‑100 and 2023‑Jan Wikipedia, using Unidic 2.1.2 word‑level tokenization plus WordPiece, in 2 M training steps.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
66,000
Hugging Face likes
65
Listed
May 13, 2024

Downloads (30-day window) over time

050k100k150kNovSepJulMayMarJan 202666,000
Show as a table
MonthDL (30d)
Dec 202537,000
Jan 202662,000
Feb 202639,000
Mar 202671,000
Apr 202689,000
May 202663,000
Jun 202672,000
Jul 202686,000
Aug 2026133,000
Sep 202643,000
Oct 202653,000
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