selfcorrexp

AI & ML interests

None defined yet.

models 25

selfcorrexp/llama3_sft_starplus_2ep

Text Generation • 8B • Updated Jan 27, 2025 • 5

selfcorrexp/llama3_sft_starplus_1ep

Text Generation • 8B • Updated Jan 26, 2025 • 3

selfcorrexp/type2_only_beta01_sftloss_step200_dpo

Text Generation • 8B • Updated Jan 18, 2025 • 6

selfcorrexp/type2_only_beta05_sftloss_step500_dpo

Text Generation • 8B • Updated Jan 17, 2025 • 6

selfcorrexp/type12_only_beta05_sftloss_step700_dpo

Text Generation • 8B • Updated Jan 17, 2025 • 5

selfcorrexp/dpo_type12_8ktype4_2ktype3_plus_sft_loss_sft350

Text Generation • 8B • Updated Jan 12, 2025 • 7

selfcorrexp/llama3_8b_star_ep2

Text Generation • 8B • Updated Dec 22, 2024 • 7

selfcorrexp/llama3_star_plus80k_double_data_ep2_2e6

Text Generation • 8B • Updated Dec 22, 2024 • 6

selfcorrexp/llama3_non_delete_rr40k_2e6_bz32_ep2

Text Generation • 8B • Updated Dec 21, 2024 • 5

selfcorrexp/llama3_balanced_regular_sft_2e6_bz32_ep2

Text Generation • 8B • Updated Dec 21, 2024 • 5

datasets 110

selfcorrexp/llama3_starplus_test2_ep3tmp07

Viewer • Updated Jan 27, 2025 • 15k • 9

selfcorrexp/llama3_starplus_test2_ep3tmp10

Viewer • Updated Jan 27, 2025 • 15k • 8

selfcorrexp/distill_40koldc2r_120kw_84kcorr

Viewer • Updated Jan 26, 2025 • 204k • 9

selfcorrexp/distill_0kc2r_120kw_84kcorr

Viewer • Updated Jan 26, 2025 • 204k • 6

selfcorrexp/llama3_starplus_test2tmp07

Viewer • Updated Jan 26, 2025 • 15k • 7

selfcorrexp/llama3_starplus_test2tmp10

Viewer • Updated Jan 26, 2025 • 15k • 5

selfcorrexp/distill_40kc2r_120kw_84kcorr

Viewer • Updated Jan 26, 2025 • 244k • 8

selfcorrexp/llama3_it_distill_first_corr_c2r

Viewer • Updated Jan 26, 2025 • 84.4k • 11

selfcorrexp/llama3_it_distill_first_wrong

Viewer • Updated Jan 26, 2025 • 205k • 11

selfcorrexp/llama3_it_distill_first_corr

Viewer • Updated Jan 26, 2025 • 84.4k • 6

View 110 datasets