selfcorrexp2/llama3_sft_more_corr_rr0k_3ep
Text Generation
•
Updated
•
29
selfcorrexp2
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
26
selfcorrexp2/llama3_sft_less_corr_rr0k_ep3_train_on_reasoning
Text Generation
•
Updated
•
33
selfcorrexp2/llama3_sft_balanced_corr_rr0k_ep3_train_on_reasoning
Text Generation
•
Updated
•
15
selfcorrexp2/llama3_sft_less_corr_rr0k_3ep
Text Generation
•
Updated
•
21
selfcorrexp2/llama3_sft_less_corr_rr60k_orm
Text Generation
•
Updated
•
7
selfcorrexp2/llama3_sft_balanced_rr60k_train_on_corr_ep3
Text Generation
•
Updated
•
129
selfcorrexp2/llama3_sft_balanced_rr0k_ep3
Text Generation
•
Updated
•
25
selfcorrexp2/llama3_open_math_sft_less_corr_rr60k_ep3
Text Generation
•
Updated
•
24
selfcorrexp2/llama3_sft_less_corr_rr0k_ep3
Text Generation
•
Updated
•
19
selfcorrexp2/llama3_sft_balanced_rr60k_ep3
Text Generation
•
Updated
•
4
datasets
184
selfcorrexp2/type12_type4_8b_type3_6k_cut_separate_pr
Updated
selfcorrexp2/type12_type4_8b_type3_2k_cut_separate_pr
Updated
selfcorrexp2/type12_type4_8b_type3_4k_cut_separate_pr
Updated
selfcorrexp2/type12_type4_8b_type3_8k_cut_separate_pr
Updated
selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_augmath_type4
Updated
selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_math_type4
Updated
selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_augmath_type3
Updated
selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_math_type3
Updated
selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_augmath_type2
Updated
selfcorrexp2/llama3_morewrong_rr60k_3ep_dpo_gen_math_type2
Updated