HF model

tokyotech-llm / Llama-3.1-Swallow-8B-v0.5

Llama 3.1 Swallow v0.5 is an 8‑billion‑parameter LLM that improves Meta’s Llama 3.1 on Japanese language and code/math reasoning while retaining English fluency, achieved through continual pre‑training and instruction‑tuned fine‑tuning on synthetic Japanese data.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
2,000
Hugging Face likes
9
Listed
Jul 1, 2025

Downloads (30-day window) over time

05k10kNovSepJulMayMarJan 20262,000
Show as a table
MonthDL (30d)
Dec 20252,000
Jan 20265,000
Feb 20262,000
Mar 20262,000
Apr 2026—
May 2026—
Jun 20269,000
Jul 2026—
Aug 20262,000
Sep 2026—
Oct 20261,000
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