HF model

llm-jp / llm-jp-4-32b-a3b-thinking

A 32‑billion‑parameter Japanese transformer LLM (llm‑jp‑4‑32b‑a3b‑thinking) from the National Institute of Informatics, pre‑trained and aligned via supervised fine‑tuning and direct preference optimization—no reinforcement learning—using a unigram byte‑fallback tokenizer.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
2,000
Hugging Face likes
40
Listed
Apr 12, 2026

Downloads (30-day window) over time

020k40kNovSepJulMayMarJan 20262,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 2026—
Mar 2026—
Apr 202610,000
May 20263,000
Jun 202636,000
Jul 202616,000
Aug 20263,000
Sep 20263,000
Oct 20262,000
Nov 20262,000

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