selfcorrexp2

selfcorrexp2's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

weqweasdas 

updated 10 datasets about 7 hours ago

selfcorrexp2/type12_type4_8b_type3_6k_cut_separate_pr

Updated about 7 hours ago

selfcorrexp2/type12_type4_8b_type3_2k_cut_separate_pr

Updated about 7 hours ago

selfcorrexp2/type12_type4_8b_type3_4k_cut_separate_pr

Updated about 7 hours ago

selfcorrexp2/type12_type4_8b_type3_8k_cut_separate_pr

Updated about 7 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_augmath_type4

Updated about 7 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_math_type4

Updated about 7 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_augmath_type3

Updated about 7 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_math_type3

Updated about 7 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_augmath_type2

Updated about 7 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_math_type2

Updated about 7 hours ago

weqweasdas 

updated 2 datasets about 8 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_augmath_type1

Updated about 8 hours ago

selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_math_type1

Updated about 8 hours ago

1231czx 

updated 2 datasets 1 day ago

selfcorrexp2/llama3_sft_less_corr_train_on_corr_dpo_gen2_augmath

Viewer • Updated 1 day ago • 19.9k • 2

selfcorrexp2/llama3_sft_less_corr_train_on_corr_dpo_gen2_math

Viewer • Updated 1 day ago • 18.7k • 1

weqweasdas 

updated 2 datasets 1 day ago

selfcorrexp2/llama3_sft_less_corr_train_on_corr_dpo_gen1_math_2nd_round_prompt

Viewer • Updated 1 day ago • 18.7k • 3

selfcorrexp2/llama3_sft_less_corr_train_on_corr_dpo_gen1_augmath_2nd_round_prompt

Viewer • Updated 1 day ago • 19.9k • 3

1231czx 

updated 2 datasets 1 day ago

selfcorrexp2/llama3_sft_less_corr_train_on_corr_dpo_gen1_augmath

Viewer • Updated 1 day ago • 7.57k • 4

selfcorrexp2/llama3_sft_less_corr_train_on_corr_dpo_gen1_math

Viewer • Updated 1 day ago • 7.5k • 4

1231czx 

updated 2 models 3 days ago

selfcorrexp2/llama3_sft_more_corr_rr0k_3ep

Text Generation • Updated 3 days ago • 29

selfcorrexp2/llama3_sft_less_corr_rr0k_ep3_train_on_reasoning

Text Generation • Updated 3 days ago • 33