HF model

sbintuitions / modernbert-ja-30m

ModernBERT‑Ja‑30M is a Japanese‑language BERT variant that blends local and global attention with RoPE, trained on 4.39 TB of Japanese/English text, supports 8,192‑token sequences, comes in sizes from 30 M to 130 M parameters, and works best with Flash Attention 2.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
3,000
Hugging Face likes
9
Listed
Mar 4, 2025

Downloads (30-day window) over time

010k20k30kNovSepJulMayMarJan 20263,000
Show as a table
MonthDL (30d)
Dec 20257,000
Jan 20262,000
Feb 20268,000
Mar 202628,000
Apr 20266,000
May 20261,000
Jun 20262,000
Jul 20262,000
Aug 20261,000
Sep 202620,000
Oct 20264,000
Nov 20263,000

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