selfcorrexp2/llama31_non_packed_bz256_lr2e6_300k_chatformat_ep2 Text Generation • 8B • Updated Dec 25, 2024 • 19
selfcorrexp2/llama3_open_math_1m_no_original_math_ep1 Text Generation • 8B • Updated Dec 27, 2024 • 18
selfcorrexp2/llama3_open_math_sft_less_corr_rr60k_ep3 Text Generation • 8B • Updated Dec 29, 2024 • 14
selfcorrexp2/llama3_sft_balanced_rr60k_train_on_corr_ep3 Text Generation • 8B • Updated Dec 29, 2024 • 20 •
selfcorrexp2/llama3_sft_balanced_corr_rr0k_ep3_train_on_reasoning Text Generation • 8B • Updated Jan 8, 2025 • 9
selfcorrexp2/llama3_sft_less_corr_rr0k_ep3_train_on_reasoning Text Generation • 8B • Updated Jan 10, 2025 • 15
selfcorrexp2/nosft_llama3sft_dpo_type3_7k_ver2_step100 Text Generation • 8B • Updated Jan 15, 2025 • 3
selfcorrexp2/type12_math_augmath_dpo_sftlossbeta05_step400 Text Generation • 8B • Updated Jan 18, 2025 • 19
selfcorrexp2/type12_math_augmath_beta05_nosftloss_step400 Text Generation • 8B • Updated Jan 18, 2025 • 17