Sofia Taouhid

thdsofia 's models 32

Sort:  Recently updated

thdsofia/MNLP_M3_dpo_model

Text Generation • 0.6B • Updated Jun 8, 2025 • 6

thdsofia/DPO_model_lr2e-6

Text Generation • 0.6B • Updated Jun 5, 2025

thdsofia/DPO_model_lr2e-6_postSFT

Text Generation • 0.6B • Updated Jun 5, 2025

thdsofia/DPO_model_lr5e-5

Text Generation • 0.6B • Updated Jun 5, 2025

thdsofia/DPO_model_lr5e-5_postSFT

Text Generation • 0.6B • Updated Jun 5, 2025

thdsofia/DPO_model_lr1e-5

Text Generation • 0.6B • Updated Jun 5, 2025

thdsofia/DPO_model_lr1e-5_postSFT

Text Generation • 0.6B • Updated Jun 5, 2025

thdsofia/orpo_both

Text Generation • 0.6B • Updated Jun 3, 2025

thdsofia/checkpoint_54k_orpo_both

Text Generation • 0.6B • Updated Jun 3, 2025

thdsofia/orpo_arg

Text Generation • 0.6B • Updated Jun 3, 2025

thdsofia/orpo_no_arg

Text Generation • 0.6B • Updated Jun 3, 2025

thdsofia/orpo_final_50k_3

Text Generation • 0.6B • Updated Jun 2, 2025 • 1

thdsofia/orpo_final_50k_2

Text Generation • 0.6B • Updated Jun 2, 2025

thdsofia/orpo_final_50k_1

Text Generation • 0.6B • Updated Jun 2, 2025

thdsofia/checkpoint_30000_orpo

Text Generation • 0.6B • Updated Jun 1, 2025

thdsofia/checkpoint_15500_orpo

Text Generation • 0.6B • Updated May 31, 2025

thdsofia/sft_final_sofia

Text Generation • 0.6B • Updated May 31, 2025

thdsofia/checkpoint_15600_sft

Text Generation • 0.6B • Updated May 31, 2025

thdsofia/general_sft

Text Generation • 0.6B • Updated May 31, 2025

thdsofia/mcqa_sciq_fast

Text Generation • 0.6B • Updated May 30, 2025

thdsofia/orpo_final

Text Generation • 0.6B • Updated May 30, 2025

thdsofia/checkpoint_5800_sft

Text Generation • 0.6B • Updated May 30, 2025

thdsofia/checkpoint_7000_orpo

Text Generation • 0.6B • Updated May 30, 2025

thdsofia/MNLP_M2_dpo_model

Text Generation • 0.6B • Updated May 26, 2025

thdsofia/dpo_20000_arg

Text Generation • 0.6B • Updated May 25, 2025

thdsofia/dpo_friday_3

Text Generation • 0.6B • Updated May 24, 2025

thdsofia/dpo_friday_2

Text Generation • 0.6B • Updated May 23, 2025

thdsofia/dpo_friday

Text Generation • 0.6B • Updated May 23, 2025

thdsofia/dpo_sunday

Text Generation • 0.6B • Updated May 21, 2025

thdsofia/dpo_model_with_10000_argilla

Text Generation • 0.6B • Updated May 19, 2025