HF model

sonoisa / t5-base-japanese

A Japanese‑language T5 model, pretrained on ~100 GB of Wikipedia and OSCAR data with SentencePiece tokenization, surpasses Google’s multilingual T5 on a news‑classification benchmark but needs fine‑tuning and may yield biased outputs.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
1,000
Hugging Face likes
57
Listed
—
Listed since the page was created

Downloads (30-day window) over time

0100k200k300kNovSepJulMayMarJan 20261,000
Show as a table
MonthDL (30d)
Dec 20253,000
Jan 20262,000
Feb 20262,000
Mar 20262,000
Apr 20263,000
May 20265,000
Jun 202681,000
Jul 2026204,000
Aug 2026216,000
Sep 20263,000
Oct 20262,000
Nov 20261,000

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