RakutenAI-7B: Extending Large Language Models for Japanese
Rakuten Group Inc., Aaron Levine, Connie Huang, Chenguang Wang,, Eduardo Batista, Ewa Szymanska, Hongyi Ding, Hou Wei Chou, Jean-Fran\c{c}ois, Pessiot, Johanes Effendi, Justin Chiu, Kai Torben Ohlhus, Karan Chopra, Keiji, Shinzato, Koji Murakami, Lee Xiong, Lei Chen, Maki Kubota
TL;DR
RakutenAI-7B is a new Japanese-focused large language model that outperforms existing open 7B models on Japanese benchmarks and includes instruction- and chat-tuned variants.
Contribution
The paper introduces RakutenAI-7B, a Japanese LLM with superior benchmark performance and released instruction- and chat-tuned models under open license.
Findings
Achieves top performance on Japanese LM benchmarks.
Includes instruction- and chat-tuned models.
Released under Apache 2.0 license.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
- 🤗Rakuten/RakutenAI-7Bmodel· 357 dl· ♡ 52357 dl♡ 52
- 🤗Rakuten/RakutenAI-7B-chatmodel· 351 dl· ♡ 66351 dl♡ 66
- 🤗Rakuten/RakutenAI-7B-instructmodel· 365 dl· ♡ 50365 dl♡ 50
- 🤗RichardErkhov/RakutenAI-7B-chat-ggufmodel· 56 dl56 dl
- 🤗RichardErkhov/Rakuten_-_RakutenAI-7B-instruct-ggufmodel· 46 dl46 dl
- 🤗RichardErkhov/Rakuten_-_RakutenAI-7B-chat-ggufmodel· 149 dl149 dl
- 🤗RichardErkhov/Rakuten_-_RakutenAI-7B-ggufmodel· 40 dl40 dl
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling