HF model

tohoku-nlp / bert-base-japanese-v2

Japanese BERT‑base (12 layers, 768 hidden, 12 heads) pretrained on 4 GB of Japanese Wikipedia (≈30 M sentences) with Unidic 2.1.2 word‑level tokenization, WordPiece sub‑tokenization, and whole‑word masking.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
9,000
Hugging Face likes
26
Listed
May 13, 2024

Downloads (30-day window) over time

010k20k30kNovSepJulMayMarJan 20269,000
Show as a table
MonthDL (30d)
Dec 202513,000
Jan 20266,000
Feb 202610,000
Mar 20269,000
Apr 20266,000
May 20266,000
Jun 20268,000
Jul 202614,000
Aug 20267,000
Sep 202624,000
Oct 202613,000
Nov 20269,000

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