single mention · post-training
Use 100% SFT data for final QAD
Uses only the full SFT blend in the final QAD training or evaluation setup.
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 the 100% SFT blend only.
Filed under post-training › supervised fine-tuning