EssentialAI: Rnj 1 Instruct

Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong performance across multiple programming languages, tool-use workflows, and agentic execution environments (e.g., mini-SWE-agent).

Rnj 1 Instruct のコンテキストウィンドウは 32,768 トークンです。

Rnj 1 Instruct は 2025年12月7日 にリリースされました。