arxiv:2411.18126
Duc Anh
vda1708
AI & ML interests
None yet
Organizations
None yet
models 14
vda1708/DRA-GRPO
2B • Updated • 3
vda1708/vicuna-7b-gsm8k-anti-cl
Updated • 1
vda1708/vda-codellama-svamp-nl
Updated • 3
vda1708/gsm8k-llama2-13b-anti-cl
Updated • 1
vda1708/vicuna-13b-gsm8k-anti-cl
Updated • 1
vda1708/gsm8k-llama2-anti-cl
Updated • 1
vda1708/vicuna-13b-gsm8k-cl
Updated • 1
vda1708/vicuna-13b-gsm8k
Updated • 1
vda1708/gsm8k-llama2-13b-cl
Updated • 1
vda1708/gsm8k-llama2-13b
Updated • 1
datasets 12
vda1708/xinlai-gsm8k-math-10k-dpo
Viewer • Updated • 10.8k • 11
vda1708/xinlai-10k-dpo
Viewer • Updated • 10.8k • 9
vda1708/Math-ED-mix-SC-Step-DPO-18K
Viewer • Updated • 18.5k • 18
vda1708/Math-ED-SC-Step-DPO-8K
Viewer • Updated • 8.42k • 18
vda1708/LEMMA-Self-Fix-70K
Viewer • Updated • 70.2k • 8
vda1708/Math-Self-Fix-8K
Viewer • Updated • 8.42k • 11
vda1708/Mercury_KATE_CDS
Viewer • Updated • 1.89k • 14
vda1708/Mercury_KATE
Viewer • Updated • 1.89k • 10
vda1708/Mercury_CDS
Viewer • Updated • 1.89k • 13
vda1708/mercury_diff
Viewer • Updated • 2.15k • 12