Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

SFT and GRPO for domain specialization

Combines supervised fine-tuning and GRPO for task-specific training.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reinforcement learning algorithm for the methods filed beside it.

Also called SFT and GRPO.

Filed under post-training › reinforcement learning algorithm