·
AI & ML interests
None yet
Organizations
1231czx/7b_dpo_iter2_4e7_bz_32_cv
Text Generation
• 9B • Updated • 1
1231czx/7b_ndpo_iter1_7e7_bz_64
Text Generation
• 9B • Updated 1231czx/7b_dpo_iter1_7e7_bz_64
Text Generation
• 9B • Updated 1231czx/7b_510k_5e6_3epoch_sft_rs_iter1_n8_2epoch
Text Generation
• 9B • Updated 1231czx/7b_510k_5e6_3epoch_sft_rs_iter1_n3_2epoch
Text Generation
• 9B • Updated 1231czx/7b_510k_5e6_3epoch_sft_rs_iter1_n1_2epoch
Text Generation
• 9B • Updated 1231czx/7b_sft3epoch_1200k_5e6
Text Generation
• 9B • Updated • 2
1231czx/7b_510k_5e6_bz64_sft4peoch
Text Generation
• 9B • Updated 1231czx/7b_510k_5e6_bz64_sft3peoch
Text Generation
• 9B • Updated 1231czx/7b_sft2epoch_1200k_5e6
Text Generation
• 9B • Updated • 2
1231czx/7b_sft1epoch_1200k_5e6
Text Generation
• 9B • Updated • 2
1231czx/7b_510k_5e6_bz64_sft1peoch_real
Text Generation
• 9B • Updated 1231czx/7b_510k_5e6_bz64_sft2peoch
Text Generation
• 9B • Updated 1231czx/7b_1200k_2e6_bz64_sft3peoch
Text Generation
• 9B • Updated 1231czx/7b_1200k_2e6_bz64_sft2peoch
Text Generation
• 9B • Updated • 1
1231czx/7b_1200k_2e6_bz64_sft1peoch
Text Generation
• 9B • Updated 1231czx/2b_dpo_iter1_400_step_sft2epoch_merged_math_gsm8k
Text Generation
• 3B • Updated 1231czx/2b_rs_merged_math_and_gsm8k_2epoch
Text Generation
• 3B • Updated 1231czx/2b_rs_merged_math_and_gsm8k_1epoch
Text Generation
• 3B • Updated 1231czx/2b_1_nll_dpo_iter2_from_sft_epoch3_100step
Text Generation
• 3B • Updated 1231czx/2b_1_nll_dpo_iter1_from_sft_epoch3_250step
Text Generation
• 3B • Updated Text Generation
• 9B • Updated • 2
Text Generation
• 9B • Updated 1231czx/2b_1_nll_dpo_iter2_200step
Text Generation
• 3B • Updated 1231czx/2b_1_nll_dpo_iter1_300step
Text Generation
• 3B • Updated 1231czx/2b_dpo_iter1_1750step
Text Generation
• 3B • Updated 1231czx/2b_dpo_iter1_1250step
Text Generation
• 3B • Updated 1231czx/2b_dpo_iter1_750step
Text Generation
• 3B • Updated 1231czx/2b_dpo_iter1_250step
Text Generation
• 3B • Updated 1231czx/2b_rs_iter1_2epoch
Text Generation
• 3B • Updated