xw1234gan/GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL download history
xw1234gan/GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL is a 3.1B-parameter text generation model by xw1234gan. In the last 30 days it was downloaded 12 times (1 in the last 7 days), and 491 times in total.
It ranks #675,827 on the Hub by monthly downloads and #251,847 among text generation models.
It has 0 likes.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.