topic · #training
Everything about training
5 connected nodes across dictionary, workflows, comparisons, prompts, tool stacks and use cases.
/ Dictionary · 5
DEFDictionaryNODE·6C8EA5
Fine-Tuning
Continuing to train a base model on your own examples to specialize its behavior.
#ai#training#models
/fine-tuningopen →
DEFDictionaryNODE·1961BA
RLHF
Reinforcement learning from human feedback, the alignment technique behind ChatGPT.
#ai#training
/rlhfopen →
DEFDictionaryNODE·72CB18
DPO (Direct Preference Optimization)
A simpler alternative to RLHF that skips the reward model.
#ai#training
/dpoopen →
DEFDictionaryNODE·2CDB38
Model Distillation
Training a small model to mimic a large one.
#ai#training
/distillationopen →
DEFDictionaryNODE·196468
LoRA
Low-Rank Adaptation: cheap fine-tuning that patches only small matrices.
#ai#training
/loraopen →