specific method · filed under post-training
LoRA fine-tuning
Parameter-efficient fine-tuning using a Low-Rank Adaptation (LoRA) adapter.
Also called LoRA adapter fine-tuning, LoRA adapter, Low-Rank Adaptation (LoRA) fine-tuning, create_lora_training_client.
- sources
- 2
- models
- 2
- labs adopt it
- 2
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1core 1
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
create_lora_training_client
corepost trainingin TinkerThinking Machines Lab
Establish a baseline, train and deploy a LoRA adapter, and evaluate task-specific improvements in minutes
usedpost trainingin NVIDIA NemotronNVIDIA
Filed alongside
Other methods under post-training :: supervised fine-tuning.
Supervised fine-tuningFine-tuningLight SFT on teacher-distribution dataRejection 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 checkpoint for RL researchSFT on MiMo-generated task dataSpecialist-model trainingSupervised fine-tuning at 256k sequence lengthToken-budget-based SFT data blending