HF model

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

Llama 3.1 Swallow is a set of 8‑B and 70‑B models that continue pre‑training Meta’s Llama 3.1 to boost Japanese language performance, then instruction‑fine‑tune on synthetic Japanese data—providing multiple released variants with improved conversational behavior comparable to gemma‑3‑27b‑it.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
7,000
Hugging Face likes
20
Listed
Jul 1, 2025

Downloads (30-day window) over time

050k100k150kNovSepJulMayMarJan 20267,000
Show as a table
MonthDL (30d)
Dec 202531,000
Jan 202619,000
Feb 20269,000
Mar 202611,000
Apr 20263,000
May 20262,000
Jun 20266,000
Jul 202614,000
Aug 2026105,000
Sep 20267,000
Oct 202613,000
Nov 20267,000

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