HF model

sbintuitions / sarashina2.2-ocr

Sarashina2.2‑OCR is a 3‑B parameter, end‑to‑end OCR model that, after human‑preference optimization, parses Japanese and English documents into Markdown while converting tables to HTML, math to LaTeX, and graphics into bounding‑box annotations, and achieves this by integrating a SigLIP2‑based vision encoder with the Sarashina2.2‑3B‑Instruct LLM for high‑resolution vision‑language understanding.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
1,000
Hugging Face likes
34
Listed
Apr 21, 2026

Downloads (30-day window) over time

1k1.5k2kNovSepJulMayMarJan 20261,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 2026—
Mar 2026—
Apr 20261,000
May 20261,000
Jun 20261,000
Jul 20261,000
Aug 20262,000
Sep 20262,000
Oct 20261,000
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