selfcorrexp

AI & ML interests

None defined yet.

selfcorrexp 's datasets 110

selfcorrexp/llama3_starplus_test2_ep3tmp07

Viewer • Updated Jan 27, 2025 • 15k • 6

selfcorrexp/llama3_starplus_test2_ep3tmp10

Viewer • Updated Jan 27, 2025 • 15k • 7

selfcorrexp/distill_40koldc2r_120kw_84kcorr

Viewer • Updated Jan 26, 2025 • 204k • 5

selfcorrexp/distill_0kc2r_120kw_84kcorr

Viewer • Updated Jan 26, 2025 • 204k • 7

selfcorrexp/llama3_starplus_test2tmp07

Viewer • Updated Jan 26, 2025 • 15k • 6

selfcorrexp/llama3_starplus_test2tmp10

Viewer • Updated Jan 26, 2025 • 15k • 6

selfcorrexp/distill_40kc2r_120kw_84kcorr

Viewer • Updated Jan 26, 2025 • 244k • 13

selfcorrexp/llama3_it_distill_first_corr_c2r

Viewer • Updated Jan 26, 2025 • 84.4k • 10

selfcorrexp/llama3_it_distill_first_wrong

Viewer • Updated Jan 26, 2025 • 205k • 8

selfcorrexp/llama3_it_distill_first_corr

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

selfcorrexp/llama3_it_first_corr_merged

Viewer • Updated Jan 26, 2025 • 87k • 6

selfcorrexp/llama3_it_firstwrong_try2_merged

Viewer • Updated Jan 26, 2025 • 110k • 7

selfcorrexp/llama3_it_1wrong_70bcollect_merged

Viewer • Updated Jan 26, 2025 • 118k • 5

selfcorrexp/llama3_it_first_corr

Viewer • Updated Jan 26, 2025 • 174k • 6

selfcorrexp/llama3_it_firstwrong_try2

Viewer • Updated Jan 26, 2025 • 330k • 5

selfcorrexp/llama3_it_1wrong_70bcollect

Viewer • Updated Jan 26, 2025 • 354k • 6

selfcorrexp/llama3_starplus_testtmp07

Viewer • Updated Jan 25, 2025 • 15k • 5

selfcorrexp/llama3_starplus_testtmp10

Viewer • Updated Jan 25, 2025 • 15k • 6

selfcorrexp/llama3_rr40k_2e6_bz32_ep2_moredatatmp10_gold_reward

Viewer • Updated Jan 23, 2025 • 15k • 5

selfcorrexp/llama3_rr40k_2e6_bz32_ep2_moredatatmp10

Viewer • Updated Jan 23, 2025 • 15k • 6

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_newtype1andtype2

Viewer • Updated Jan 17, 2025 • 23.8k • 13

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_newtype2

Viewer • Updated Jan 17, 2025 • 9.31k • 7

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_newtype1

Viewer • Updated Jan 17, 2025 • 14.5k • 7

selfcorrexp/dpo_final_scalingtmp07_with_rewards

Viewer • Updated Jan 15, 2025 • 325k • 6

selfcorrexp/dpo_final_scalingtmp07

Viewer • Updated Jan 15, 2025 • 325k • 6

selfcorrexp/type12_8ktype4_2ktype3_new_350tmp10

Viewer • Updated Jan 12, 2025 • 15k • 6

selfcorrexp/type12_type4_8b_type3_1k_cut_separate_pr

Viewer • Updated Jan 12, 2025 • 34.8k • 7

selfcorrexp/type12_type4_8b_type3_3k_cut_separate_pr

Viewer • Updated Jan 12, 2025 • 34.8k • 8

selfcorrexp/type12_type4_8b_type3_4k_cut_separate_pr

Viewer • Updated Jan 12, 2025 • 35.8k • 12

selfcorrexp/type12_type4_8b_type3_2k_cut_separate_pr

Viewer • Updated Jan 12, 2025 • 33.8k • 7