atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-False download history

atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-False is a 1.7B-parameter text generation model by atrost. In the last 30 days it was downloaded 12 times (3 in the last 7 days), and 57 times in total.

It ranks #670,866 on the Hub by monthly downloads and #248,733 among text generation models.

It has 0 likes.

It is a fine-tune of Qwen/Qwen3-1.7B-Base.

Open atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-False on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.