specific method · filed under post-training
SFT checkpoint for RL research
A supervised fine-tuning checkpoint presented as a starting point for reinforcement-learning research rather than as a finished assistant.
Also called SFT starting point for RL research.
- source
- 1
- models
- 2
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
this checkpoint is an SFT starting point for RL research, not a finished assistant
coreunclearin MiMo-V2.6-Distill-Qwen-9BXiaomi
Filed alongside
Other methods under post-training :: supervised fine-tuning.
Supervised fine-tuningFine-tuningLight SFT on teacher-distribution dataLoRA fine-tuningRejection samplingSelf-correction cold startSFT bootstrapping with synthetic dataAdversarial fine-tuningAutoregressive fine-tuningCold-started SFT modelEvaluation-based early stoppingFine-tuning with demographically balanced datasetsFrozen-network warmup for new special tokensInstruction hierarchy trainingInstruction-following fine-tuningLightweight speaker fine-tuningPrompt-based cold start for tool useReasoning-data system promptSafety training to an internal specificationSFT on MiMo-generated task dataSpecialist-model trainingSupervised fine-tuning at 256k sequence lengthToken-budget-based SFT data blending