SongTonyLi/SFT_D1chosenThenDPO_D2a_Instruct_argilla_math_results download history

SongTonyLi/SFT_D1chosenThenDPO_D2a_Instruct_argilla_math_results is an 8.0B-parameter text generation model by SongTonyLi. In the last 30 days it was downloaded 12 times (7 in the last 7 days), and 50 times in total.

It ranks #653,410 on the Hub by monthly downloads and #238,415 among text generation models.

It has 0 likes.

It is a fine-tune of SongTonyLi/SFT_D1chosen_math_cosineLR_instruct.

Open SongTonyLi/SFT_D1chosenThenDPO_D2a_Instruct_argilla_math_results on Hugging Face