single mention · post-training
SFT checkpoint intended as an RL starting point
Provides an SFT checkpoint as a starting point for reinforcement-learning research rather than as a finished assistant.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See supervised fine-tuning for the methods filed beside it.
Also called SFT starting point for RL research.
Filed under post-training › supervised fine-tuning