Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning https://www.arxiv.org/abs/2402.13669 https://www.alphaxiv.org/ru/overview/2402.13669 https://github.com/sail-sg/sdft
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning…
0 viewsОткрыть в Telegram →
Из этого канала
- #6090Dreaming in Code for Curriculum Learning in Open-Ended Worlds…
Dreaming in Code for Curriculum Learning in Open-Ended Worlds https://www.arxiv.org/abs/2602.08194 https://www.alphaxiv.org/ru/overview/2602.08194…
- #6091https://github.com/researchim-ai/models-at-home добавил в студию чуть больше…
https://github.com/researchim-ai/models-at-home добавил в студию чуть больше инфы из той статьи про фронтиры + появилась страница с настройками)
- #6092Understanding Self-Distillation and Privileged Information Distillation…
Understanding Self-Distillation and Privileged Information Distillation https://emilianopp.github.io/Privileged-Information-Distillation-and-Self-Distillation/
- #6088Self-Distillation Enables Continual Learning…
Self-Distillation Enables Continual Learning https://www.arxiv.org/abs/2601.19897 https://www.alphaxiv.org/ru/overview/2601.19897…
- #6087Privileged Information Distillation for Language Models…
Privileged Information Distillation for Language Models https://arxiv.org/abs/2602.04942 https://www.alphaxiv.org/ru/overview/2602.04942