selfcorrexp on Hugging Face: downloads and rankings
selfcorrexp has 25 tracked models, downloaded 266 times in the last 30 days and 1,226 times in total; 110 datasets, downloaded 2,413 times in the last 30 days. selfcorrexp Wrapped: the last 12 months.
Models by downloads in the last 30 days
- selfcorrexp/llama3_non_delete_rr40k_2e6_bz32_ep3 19 downloads, text generation
- selfcorrexp/type12_only_beta05_sftloss_step700_dpo 15 downloads, text generation
- selfcorrexp/llama3_rr10k_2e6_bz32_ep2 14 downloads, text generation
- selfcorrexp/llama3_balanced_regular_sft_2e6_bz32_ep2 13 downloads, text generation
- selfcorrexp/type2_only_beta01_sftloss_step200_dpo 12 downloads, text generation
- selfcorrexp/llama3_8b_star_ep2 12 downloads, text generation
- selfcorrexp/dpo_type12_8ktype4_2ktype3_plus_sft_loss_sft350 12 downloads, text generation
- selfcorrexp/llama3_rr40k_2e6_bz32_ep1 11 downloads, text generation
- selfcorrexp/llama3_non_balanced_rr10k_2e6_bz32_ep2 11 downloads, text generation
- selfcorrexp/llama3_rr10k_2e6_bz32_ep3 11 downloads, text generation
- selfcorrexp/llama3_non_delete_sft_2e6_bz32_ep3 10 downloads, text generation
- selfcorrexp/llama3_rr40k_2e6_bz32_ep2 10 downloads, text generation
- selfcorrexp/llama3_star_plus80k_double_data_ep2_2e6 10 downloads, text generation
- selfcorrexp/llama3_non_delete_rr40k_2e6_bz32_ep2 10 downloads, text generation
- selfcorrexp/llama3_non_delete_sft_2e6_bz32_ep2 9 downloads, text generation
- selfcorrexp/llama3_non_balanced_rr80k_2e6_bz32_ep2 9 downloads, text generation
- selfcorrexp/llama3_balanced_regular_sft_2e6_bz32_ep3 9 downloads, text generation
- selfcorrexp/llama3_non_balanced_regular_sft_2e6_bz32_ep3 9 downloads, text generation
- selfcorrexp/llama3_sft_starplus_1ep 9 downloads, text generation
- selfcorrexp/llama3_non_balanced_rr10k_2e6_bz32_ep3 9 downloads, text generation
- selfcorrexp/llama3_non_balanced_rr40k_2e6_bz32_ep3 9 downloads, text generation
- selfcorrexp/llama3_non_balanced_rr40k_2e6_bz32_ep2 9 downloads, text generation
- selfcorrexp/llama3_non_balanced_regular_sft_2e6_bz32_ep2 8 downloads, text generation
- selfcorrexp/llama3_sft_starplus_2ep 8 downloads, text generation
- selfcorrexp/type2_only_beta05_sftloss_step500_dpo 8 downloads, text generation
Datasets by downloads in the last 30 days
- selfcorrexp/llama3_additional_rr40k_non_delete_sft 94 downloads
- selfcorrexp/llama3_additional_rr40k_NON_balanced_sft 61 downloads
- selfcorrexp/llama3_it_firstwrong_try2 61 downloads
- selfcorrexp/llama3_additional_rr80k_NON_balanced_sft 61 downloads
- selfcorrexp/llama3_additional_rr40k_non_delete_sft_chat_format 59 downloads
- selfcorrexp/baseline_star 58 downloads
- selfcorrexp/llama_it_8b_temp07_math_scaling 51 downloads
- selfcorrexp/llama3_regular_NON_balanced_sft 50 downloads
- selfcorrexp/llama3_additional_rr10k_NON_balanced_sft 50 downloads
- selfcorrexp/baseline_star_rr80k 49 downloads
- selfcorrexp/llama3_v2_rlhflow_math1 49 downloads
- selfcorrexp/llama3_additional_rr40k_balanced_sft 45 downloads
- selfcorrexp/llama3_prompt_first_wrong_math1 44 downloads
- selfcorrexp/llama3_regular_balanced_sft_chat_format 41 downloads
- selfcorrexp/llama3_prompt_first_corr_math1_regular_processed 41 downloads
- selfcorrexp/llama3_it_distill_first_corr_c2r 37 downloads
- selfcorrexp/dpo_math1pair_and_augmath 36 downloads
- selfcorrexp/llama31_prompt_first_wrong_math1 35 downloads
- selfcorrexp/llama3_non_delete_4_ORM_training 34 downloads
- selfcorrexp/llama3_prompt_corr_prompt 34 downloads
- selfcorrexp/dpo_1pair_per_idx_math_and_augmath 33 downloads
- selfcorrexp/llama3_non_balanced_rr10k_2e6_bz32_ep3tmp07 33 downloads
- selfcorrexp/llama3_regular_balanced_sft 32 downloads
- selfcorrexp/llama3_additional_rr10k_balanced_sft 31 downloads
- selfcorrexp/llama3_8b_non_delete_40k_scaling_tmp07 30 downloads
- selfcorrexp/llama3_regular_NON_balanced_sft_4_ORM_training 30 downloads
- selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_math_1_type4 30 downloads
- selfcorrexp/llama3_prompt_first_wrong_math2 29 downloads
- selfcorrexp/dpo_final_scalingtmp07 28 downloads
- selfcorrexp/llama3_it_distill_first_wrong 28 downloads
- selfcorrexp/llama3_prompt_first_corr_math1_processed 28 downloads
- selfcorrexp/llama3_prompt_first_wrong_prompt1 27 downloads
- selfcorrexp/llama31_prompt_first_wrong_math2 26 downloads
- selfcorrexp/llama3_prompt_first_wrong_math2_processed 25 downloads
- selfcorrexp/llama3_it_firstwrong_try2_merged 24 downloads
- selfcorrexp/llama3_it_1wrong_70bcollect 23 downloads
- selfcorrexp/llama3_8b_non_delete_40k_scaling_tmp07_2 23 downloads
- selfcorrexp/llama3_8b_non_delete_40k_scaling_tmp07_1 23 downloads
- selfcorrexp/llama3_starplus_testtmp07 23 downloads
- selfcorrexp/llama3_non_delete_regular_balanced_sft 22 downloads
- selfcorrexp/llama3_prompt_first_wrong_prompt2 22 downloads
- selfcorrexp/distill_40koldc2r_120kw_84kcorr 21 downloads
- selfcorrexp/distill_40kc2r_120kw_84kcorr 20 downloads
- selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_augmath_2 20 downloads
- selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_augmath_1_type2 20 downloads
- selfcorrexp/type1_and_type2_separate_pr 20 downloads
- selfcorrexp/llama31_prompt_first_corr_math1 20 downloads
- selfcorrexp/llama3_it_8b_tmp10_n3 19 downloads
- selfcorrexp/dpo_final_scalingtmp07_with_rewards 19 downloads
- selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_gen_math_1_type4_cut 18 downloads