Release Of "Fugaku-LLM" – A Large Language Model Trained On The Supercomputer "Fugaku"

Fugaku-LLM is an open-source large language model trained on the Fugaku supercomputer, offering enhanced Japanese language capabilities for research and business applications. It provides high-performance natural language processing.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is Release of "Fugaku-LLM" – a large language model trained on the supercomputer "Fugaku"?

Fugaku-LLM is a large language model developed by a collaborative team including Tokyo Institute of Technology and RIKEN, trained on Japan's flagship supercomputer, Fugaku. This model boasts enhanced Japanese language abilities, achieving a high score of 5.5 on the Japanese MT-Bench, with a remarkable 9.18 for humanities and social sciences tasks. With 13 billion parameters, it surpasses many other Japanese-developed models. Uniquely, Fugaku-LLM was trained from scratch using proprietary Japanese data, ensuring transparency and safety, unlike models relying on continual learning from existing open models. It is available for both research and commercial use, with its source code on GitHub and the model on Hugging Face, promoting further development and innovative applications in AI.

Best used for

Ideal for developers and data scientists who need to build advanced AI applications, conduct cutting-edge research in natural language processing, and integrate a powerful, transparent LLM into their projects. Especially valuable for applications requiring high-performance Japanese language understanding and generation.

Common actions

develop AI applications

process Japanese language

conduct AI research

integrate LLM

AI infrastructureJapanese NLPFugakumachine learningresearch toolopen-sourceLLMsupercomputer

Capabilities

Key features

13 billion parameters
Enhanced Japanese language ability
Trained on Fugaku supercomputer
Distributed parallel learning
Commercial use permitted
Open source code

Target Audience

developerdata scientistresearcherstartup founder

Integrations

githubhugging-face

Pricing & Plans

Open Source

FAQs

What makes Fugaku-LLM unique compared to other Japanese LLMs?

Fugaku-LLM stands out because it was trained from scratch using proprietary Japanese data, rather than continually training on existing open models. This approach ensures greater transparency and safety in its learning process, and it has 13 billion parameters, making it larger than many other Japanese models.

Can Fugaku-LLM be used for commercial projects?

Yes, Fugaku-LLM is explicitly stated to be available for both research and commercial purposes. Users are required to comply with its license, but its open-source nature and permission for commercial use make it a versatile option for various applications.

Where can I access the Fugaku-LLM model and its source code?

The source code for Fugaku-LLM is publicly available on GitHub, allowing developers to inspect and contribute to its development. The trained model itself can be accessed and utilized through Hugging Face, a popular platform for AI datasets and models.

Trending

Subcategories trending in Coding & Development

Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce