跳到正文
Cohere Labs:官方研究博客·· 2026-10-10AI 評分48

North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)

North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)

AI 導讀

North Small Translate 是一款具指令跟隨能力的開放權重 LLM 機器翻譯模型,建基於 Cohere Command A Plus 的同一基礎架構;該 MoE 架構共有 218 billion 個參數,當中 25 billion 個為活躍參數。

正文

Sep 12, 2026

We present North Small Translate, an open-weight, LLM-based machine translation (MT) model with instruction-following capabilities built on the same foundation as Cohere's Command A Plus, a mixture-of-experts architecture with 25 billion active parameters out of 218 billion total parameters.

Authors

Tom Kocmi, Alexandre Bérard, Phil Blunsom, Samuel Cahyawijaya, Shaun Cassini, Nicholas Frosst, Ona de Gibert, Aidan Gomez, Nithya Govindarajan, Shun Kiyono, Olivia Lasche, Lawrence Rogers, Kelly Marchisio, Nikita Moghe, Yash More, Camila Moran-Hidalgo, Yiyang Nan, Michael Sachs, Trisha Starostina, Daan van Stigt, Spencer Rarrick, Sebastian Vincent, Ivan Zhang

Abstract

We present North Small Translate, an open-weight, LLM-based machine translation (MT) model with instruction-following capabilities built on the same foundation as Cohere's Command A Plus, a mixture-of-experts architecture with 25 billion active parameters out of 218 billion total parameters. North Small Translate is trained using difficulty sampling to obtain challenging documents and a five-step training protocol combining supervised fine-tuning, direct preference optimization, and online reinforcement learning. We prioritized throughput through a non-reasoning base model and supplemented with optional agentic capabilities to unlock translation quality gains. North Small Translate is trained to perform MT-related tasks, including post-editing and quality estimation, as well as related tasks such as general instruction following. The model achieves top MT performance across 50 languages in the class of models under 1T parameters, with no need to run expensive reasoning at inference time.

Related works

來源:Cohere Labs:官方研究博客 · cohere.com