selfcorrexp/llama3_sft_starplus_2ep
Text Generation • 8B • Updated
AI & ML interests
None defined yet.
models 25
selfcorrexp/llama3_sft_starplus_1ep
Text Generation • 8B • Updated
selfcorrexp/type2_only_beta01_sftloss_step200_dpo
Text Generation • 8B • Updated
• 1
selfcorrexp/type2_only_beta05_sftloss_step500_dpo
Text Generation • 8B • Updated
• 1
selfcorrexp/type12_only_beta05_sftloss_step700_dpo
Text Generation • 8B • Updated
• 1
selfcorrexp/dpo_type12_8ktype4_2ktype3_plus_sft_loss_sft350
Text Generation • 8B • Updated
• 1
selfcorrexp/llama3_8b_star_ep2
Text Generation • 8B • Updated
• 1
selfcorrexp/llama3_star_plus80k_double_data_ep2_2e6
Text Generation • 8B • Updated
• 2
selfcorrexp/llama3_non_delete_rr40k_2e6_bz32_ep2
Text Generation • 8B • Updated
selfcorrexp/llama3_balanced_regular_sft_2e6_bz32_ep2
Text Generation • 8B • Updated
• 2
datasets 110
selfcorrexp/llama3_starplus_test2_ep3tmp07
Viewer
• Updated
• 15k • 4
selfcorrexp/llama3_starplus_test2_ep3tmp10
Viewer
• Updated
• 15k • 4
selfcorrexp/distill_40koldc2r_120kw_84kcorr
Viewer
• Updated
• 204k • 9
selfcorrexp/distill_0kc2r_120kw_84kcorr
Viewer
• Updated
• 204k • 5
selfcorrexp/llama3_starplus_test2tmp07
Viewer
• Updated
• 15k • 4
selfcorrexp/llama3_starplus_test2tmp10
Viewer
• Updated
• 15k • 4
selfcorrexp/distill_40kc2r_120kw_84kcorr
Viewer
• Updated
• 244k • 9
selfcorrexp/llama3_it_distill_first_corr_c2r
Viewer
• Updated
• 84.4k • 5
selfcorrexp/llama3_it_distill_first_wrong
Viewer
• Updated
• 205k • 6
selfcorrexp/llama3_it_distill_first_corr
Viewer
• Updated
• 84.4k • 4