HF model

ku-nlp / deberta-v3-base-japanese

Japanese DeBERTa V3 base pre‑trained on 540 B tokens from LLM‑jp v1.0, trained with a modified DeBERTa V3 setup, uses a unigram byte‑fallback tokenizer (no morphological analyzer), and is fine‑tuned for JGLUE NLU tasks.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
13,000
Hugging Face likes
21
Listed
May 13, 2024

Downloads (30-day window) over time

010k20k30kNovSepJulMayMarJan 202613,000
Show as a table
MonthDL (30d)
Dec 202516,000
Jan 202613,000
Feb 20266,000
Mar 20263,000
Apr 202621,000
May 20263,000
Jun 20265,000
Jul 202610,000
Aug 20264,000
Sep 20265,000
Oct 20264,000
Nov 202613,000

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