For fine-tuning SFT, we focused on extending machine translation capabilities by prepping data focused on post-editing, error detection, and terminology. We also went through multiple steps of reinforcement learning and DPO targeted towards errors the model exhibited. (2/6) pic.twitter.com/Jj28u0Avv8
— Cohere (@cohere) 3 octobre 2026
For fine-tuning SFT, we focused on extending machine translation capabilities by prepping data focused on post-editing, error detection, and terminology. We also went through multiple steps of reinforcement learning and DPO targeted towards errors the model exhibited. (2/6)