HF model

line-corporation / clip-japanese-base

LY Corporation’s clip‑japanese‑base is a Japanese CLIP model trained on ~1 B image‑text pairs, using an Eva02‑B transformer image encoder with a 12‑layer BERT text encoder, achieving R@1 0.30 on STAIR, 0.89 accuracy on Recruit and 0.58 accuracy on ImageNet‑1K, and supporting zero‑shot image classification and retrieval.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
34,000
Hugging Face likes
30
Listed
May 17, 2024

Downloads (30-day window) over time

10k20k30k40kNovSepJulMayMarJan 202634,000
Show as a table
MonthDL (30d)
Dec 202521,000
Jan 202618,000
Feb 202620,000
Mar 202623,000
Apr 202619,000
May 202626,000
Jun 202624,000
Jul 202626,000
Aug 202625,000
Sep 202627,000
Oct 202629,000
Nov 202634,000

Downloads over the 30 days before the last snapshot of each month.

Popular in the same category

Resources in similar research fields

Related slides and articles

Ones that name this resource in their titles, and ones close to its description

Learn from slides & articles