arxiv:2403.15484

RakutenAI-7B: Extending Large Language Models for Japanese

Published on Mar 21

· Submitted by

akhaliq on Mar 26

Upvote

Authors:

Connie Huang ,

Chenguang Wang ,

Hongyi Ding ,

Hou Wei Chou ,

Johanes Effendi ,

Justin Chiu ,

Kai Torben Ohlhus ,

Keiji Shinzato ,

Maksim Tkachenko ,

Prathyusha Jwalapuram

Abstract

We introduce RakutenAI-7B, a suite of Japanese-oriented large language models that achieve the best performance on the Japanese LM Harness benchmarks among the open 7B models. Along with the foundation model, we release instruction- and chat-tuned models, RakutenAI-7B-instruct and RakutenAI-7B-chat respectively, under the Apache 2.0 license.

View arXiv page View PDF Add to collection

Community

librarian-bot

Mar 27

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

sonsus

Mar 27

Seem there's not pretty much details in retrofitting process... not sure is this mean they did the standard practice on doing this or just they did not disclosed it. One clear thing about is that they did use huge scale of filtered japanese corpus (~175 B tokens).