gpt-neox-japanese-2.7b is a 2.7 billion parameter causal language model based on the GPT-NeoX architecture, pretrained specifically on Japanese text. It is designed for Japanese text generation and other NLP tasks. The model is available on Hugging Face and can be used with the Transformers library by developers working with Japanese language applications.
In the Text generation space, Gpt Neox Japanese 2.7b takes a focused approach. It focuses on generating high-quality Japanese text using an open-source large language model. Gpt Neox Japanese 2.7b is an open-source project aimed at developers. Gpt Neox Japanese 2.7b is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
Behind Gpt Neox Japanese 2.7b is ABEJA, based in Japan, and it first shipped in 2018. Development happens publicly on GitHub with 162.8k stars and 745 commits in the last 90 days. Among its 3 catalogued features are japanese text generation, causal language modeling, and pretrained on Japanese data.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do