selfcorrexp

AI & ML interests

None defined yet.

selfcorrexp 's datasets 110

selfcorrexp/llama3_it_8b_tmp07_n3

Viewer • Updated Dec 29, 2024 • 15k • 6

selfcorrexp/llama3_it_8b_tmp10_n3

Viewer • Updated Dec 29, 2024 • 15k • 6

selfcorrexp/llama3_regular_balanced_sft_4_ORM_training

Viewer • Updated Dec 29, 2024 • 174k • 7

selfcorrexp/llama3_regular_NON_balanced_sft_4_ORM_training

Viewer • Updated Dec 29, 2024 • 327k • 8

selfcorrexp/llama3_non_delete_4_ORM_training

Viewer • Updated Dec 29, 2024 • 191k • 6

selfcorrexp/llama3_regular_balanced_sft_chat_format

Viewer • Updated Dec 23, 2024 • 174k • 7

selfcorrexp/llama3_additional_rr40k_non_delete_sft_chat_format

Viewer • Updated Dec 23, 2024 • 231k • 7

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_augmath_2

Viewer • Updated Dec 22, 2024 • 25.5k • 5

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_augmath_1

Viewer • Updated Dec 22, 2024 • 25.5k • 5

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_math_2

Viewer • Updated Dec 22, 2024 • 21.4k • 5

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_math_1

Viewer • Updated Dec 22, 2024 • 21.4k • 5

selfcorrexp/llama31_prompt_first_corr_math1

Viewer • Updated Dec 22, 2024 • 60k • 4

selfcorrexp/llama31_prompt_first_wrong_math2

Viewer • Updated Dec 22, 2024 • 118k • 3

selfcorrexp/llama31_prompt_first_wrong_math1

Viewer • Updated Dec 22, 2024 • 110k • 5

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_math_2nd_round_prompt

Viewer • Updated Dec 21, 2024 • 21.4k • 3

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_augmath_2nd_round_prompt

Viewer • Updated Dec 21, 2024 • 25.5k • 5

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_math_base

Viewer • Updated Dec 21, 2024 • 7.01k • 5

selfcorrexp/baseline_star_rr80k

Viewer • Updated Dec 21, 2024 • 257k • 6

selfcorrexp/baseline_star_rr8ou0k

Updated Dec 21, 2024 • 4

selfcorrexp/baseline_star

Viewer • Updated Dec 21, 2024 • 176k • 6

selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_augmath_base

Viewer • Updated Dec 21, 2024 • 15.1k • 5

selfcorrexp/llama3_additional_rr40k_non_delete_sft

Viewer • Updated Dec 20, 2024 • 231k • 8

selfcorrexp/llama3_non_delete_regular_balanced_sft

Viewer • Updated Dec 20, 2024 • 191k • 7

selfcorrexp/llama3_additional_rr80k_NON_balanced_sft

Viewer • Updated Dec 20, 2024 • 407k • 8

selfcorrexp/llama31_prompt_first_wrong_prompt2

Viewer • Updated Dec 20, 2024 • 60.4k • 5

selfcorrexp/llama31_prompt_first_wrong_prompt1

Viewer • Updated Dec 20, 2024 • 60k • 5

selfcorrexp/llama31_prompt_corr_prompt

Viewer • Updated Dec 20, 2024 • 60k • 4

selfcorrexp/llama3_non_balanced_rr10k_2e6_bz32_ep3tmp07

Viewer • Updated Dec 20, 2024 • 15k • 5

selfcorrexp/llama3_non_balanced_rr10k_2e6_bz32_ep3tmp10

Viewer • Updated Dec 20, 2024 • 15k • 5

selfcorrexp/llama3_v2_rlhflow_math2

Viewer • Updated Dec 20, 2024 • 7.5k • 5