hdong0/deepseek-Qwen-1.5B-baseline-thin-Open-R1-GRPO_deepscaler_mu_8_constant_lr_warmed download history
hdong0/deepseek-Qwen-1.5B-baseline-thin-Open-R1-GRPO_deepscaler_mu_8_constant_lr_warmed is a 1.9B-parameter text generation model by hdong0. In the last 30 days it was downloaded 27 times (11 in the last 7 days), and 111 times in total.
It ranks #334,548 on the Hub by monthly downloads and #93,976 among text generation models.
It has 0 likes.
It is a fine-tune of hdong0/deepseek-Qwen2.5-1.5B-baseline-thin-init.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.