arxiv:2410.01180
Kangda Wei
kangdawei
AI & ML interests
None yet
Organizations
models 50
kangdawei/DRA-GRPO-8B
Text Generation • 8B • Updated • 14
kangdawei/DRA-GRPO-7B
Text Generation • 8B • Updated • 20
kangdawei/MMR-Sigmoid-DAPO-7B
Text Generation • 8B • Updated • 59
kangdawei/MMR-Sigmoid-DR-GRPO-8B
Text Generation • 8B • Updated • 13
kangdawei/MMR-Sigmoid-DAPO-8B
Text Generation • 8B • Updated • 25 •
kangdawei/MMR-Sigmoid-DAPO
Text Generation • 2B • Updated • 19
kangdawei/MMR-Sigmoid-GRPO-8B
Text Generation • 8B • Updated • 18 • 1
kangdawei/MMR-Sigmoid-GRPO-7B
Text Generation • 8B • Updated • 18
kangdawei/MMR-Sigmoid-DR-GRPO-7B
Text Generation • 8B • Updated • 17
kangdawei/DAPO-8B
Text Generation • 8B • Updated • 43 •
datasets 0
None public yet