HF model

tohoku-nlp / bert-base-japanese-char-v2

A BERT‑base Japanese model (12 layers, 768‑dim hidden states, 12 heads) trained on 30 M Wikipedia sentences (~4 GB) with Unidic 2.1.2 word‑level tokenization followed by character‑level tokenization and whole‑word masking, using 512‑token sequences, 256 batches, and 1 M training steps.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
55,000
Hugging Face likes
6
Listed
May 13, 2024

Downloads (30-day window) over time

0100k200k300kNovSepJulMayMarJan 202655,000
Show as a table
MonthDL (30d)
Dec 2025128,000
Jan 202633,000
Feb 202655,000
Mar 202646,000
Apr 202649,000
May 202666,000
Jun 202667,000
Jul 2026244,000
Aug 202668,000
Sep 202668,000
Oct 202662,000
Nov 202655,000

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