HF model

line-corporation / line-distilbert-base-japanese

LINE DistilBERT Japanese is a 66‑million‑parameter DistilBERT model pre‑trained on 131 GB of Japanese web text using an in‑house BERT‑base teacher, evaluated on JGLUE, tokenized with MeCab Unidic and SentencePiece, and released under the Apache 2.0 license.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
14,000
Hugging Face likes
50
Listed
—
Listed since the page was created

Downloads (30-day window) over time

020k40kNovSepJulMayMarJan 202614,000
Show as a table
MonthDL (30d)
Dec 202535,000
Jan 202632,000
Feb 202640,000
Mar 202615,000
Apr 202618,000
May 20266,000
Jun 202616,000
Jul 20268,000
Aug 20267,000
Sep 20268,000
Oct 20264,000
Nov 202614,000

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