mytestdpo/llsfttype12_gsm_auggsm_dpo_sftlossbeta05_step500
Text Generation • 8B • Updated • 6
AI & ML interests
None defined yet.
models 7
mytestdpo/type2_only_llama3it_gsm8k_beta05_sftloss_step500_dpo
Text Generation • 8B • Updated • 12
mytestdpo/type12_only_beta05_sftloss_step500
Text Generation • 8B • Updated • 8
mytestdpo/type12_7k_type3_5ktype4_beta05_sftloss_step450_dpo
Text Generation • 8B • Updated • 8
mytestdpo/llama3_orm_tmp10_2
Text Generation • 8B • Updated • 10 •
mytestdpo/llama3_orm_tmp10
Text Generation • 8B • Updated • 10 •
mytestdpo/llama3_8b_dpo_iter2
Updated
datasets 156
mytestdpo/qwmathbase_raw_raft_step160_olympiadbench
Viewer • Updated • 675 • 8
mytestdpo/qwmathbase_raw_raft_step160_minerva_math
Viewer • Updated • 272 • 14
mytestdpo/qwmathbase_raw_raft_step160_amc23
Viewer • Updated • 40 • 13
mytestdpo/qwmathbase_raw_raft_step160_math500
Viewer • Updated • 500 • 52
mytestdpo/qwmathbase_raw_raft_step160_aime24
Viewer • Updated • 30 • 27
mytestdpo/qwmathbase_raw_raft_step40_olympiadbench
Viewer • Updated • 675 • 21
mytestdpo/qwmathbase_raw_raft_step40_minerva_math
Viewer • Updated • 272 • 42
mytestdpo/qwmathbase_raw_raft_step40_amc23
Viewer • Updated • 40 • 16
mytestdpo/qwmathbase_raw_raft_step40_math500
Viewer • Updated • 500 • 14
mytestdpo/qwmathbase_raw_raft_step40_aime24
Viewer • Updated • 30 • 12