mytestdpo

AI & ML interests

None defined yet.

Recent Activity

Chenlu123 submitted a paper 2 months ago

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL

HanningZhang authored a paper about 1 year ago

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

1231czx updated a dataset about 1 year ago

mytestdpo/qwmathbase_raw_raft_step160_olympiadbench

View all activity

models 7

mytestdpo/llsfttype12_gsm_auggsm_dpo_sftlossbeta05_step500

Text Generation • 8B • Updated Jan 19, 2025

mytestdpo/type2_only_llama3it_gsm8k_beta05_sftloss_step500_dpo

Text Generation • 8B • Updated Jan 17, 2025 • 2

mytestdpo/type12_only_beta05_sftloss_step500

Text Generation • 8B • Updated Jan 17, 2025 • 2

mytestdpo/type12_7k_type3_5ktype4_beta05_sftloss_step450_dpo

Text Generation • 8B • Updated Jan 17, 2025 • 2

mytestdpo/llama3_orm_tmp10_2

Text Generation • 8B • Updated Jan 6, 2025 •

mytestdpo/llama3_orm_tmp10

Text Generation • 8B • Updated Jan 6, 2025 • 2 •

mytestdpo/llama3_8b_dpo_iter2

Updated Dec 26, 2024

datasets 156

mytestdpo/qwmathbase_raw_raft_step160_olympiadbench

Viewer • Updated Mar 19, 2025 • 675 • 43

mytestdpo/qwmathbase_raw_raft_step160_minerva_math

Viewer • Updated Mar 19, 2025 • 272 • 112

mytestdpo/qwmathbase_raw_raft_step160_amc23

Viewer • Updated Mar 19, 2025 • 40 • 30

mytestdpo/qwmathbase_raw_raft_step160_math500

Viewer • Updated Mar 19, 2025 • 500 • 4

mytestdpo/qwmathbase_raw_raft_step160_aime24

Viewer • Updated Mar 19, 2025 • 30 • 4

mytestdpo/qwmathbase_raw_raft_step40_olympiadbench

Viewer • Updated Mar 19, 2025 • 675 • 128

mytestdpo/qwmathbase_raw_raft_step40_minerva_math

Viewer • Updated Mar 19, 2025 • 272 • 10

mytestdpo/qwmathbase_raw_raft_step40_amc23

Viewer • Updated Mar 19, 2025 • 40 • 9

mytestdpo/qwmathbase_raw_raft_step40_math500

Viewer • Updated Mar 19, 2025 • 500 • 39

mytestdpo/qwmathbase_raw_raft_step40_aime24

Viewer • Updated Mar 19, 2025 • 30 • 6

View 156 datasets