hdong0/deepseek-Llama-8B-baseline-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr download history

hdong0/deepseek-Llama-8B-baseline-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr is an 8.3B-parameter text generation model by hdong0. In the last 30 days it was downloaded 27 times (12 in the last 7 days), and 88 times in total.

It ranks #334,611 on the Hub by monthly downloads and #93,620 among text generation models.

It has 0 likes.

It is a fine-tune of hdong0/deepseek-Llama-8B-baseline-thin-init.

Open hdong0/deepseek-Llama-8B-baseline-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr on Hugging Face

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