sangmichaelxie/doremi
Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets
HTMLMIT
Stargazers
- erichoceanNorth Carolina
- stefan-itBavarian Oberland, Germany
- tiendung
- Hyperfluxe
- ScottishFold007Shanghai
- whongyi
- weikang-wang
- dumpmemory
- adamsyu
- denisfitz57
- rkrishnasankaBoston
- bbo0924
- Jiaxin-WenBeijing, China
- u-brixton
- xyease
- cliangyu
- debackerlBelgium
- ahmedoumarMarrakech
- prnake
- yavuzCodiin
- WissamAntounParis-France
- jaygala24Abu Dhabi, United Arab Emirates
- SushantDaga
- chuanmingliuMars, Solar
- jfozard
- AndromedaPerseusUnited States
- C00reNUT
- Haoxiang-WangUrbana
- zhxiemlShanghai
- jordane95
- ifrit98Disneyland
- rom1504Paris
- IndieMinimalist
- jmanhype
- markdouthwaiteManchester, UK
- shuxiaoboJingxiang Square of Beijing China