hdong0/deepseek-Llama-8B-Open-R1-GRPO_deepscaler_1000steps_lr1e-6_kl1e-3_acc_old download history
hdong0/deepseek-Llama-8B-Open-R1-GRPO_deepscaler_1000steps_lr1e-6_kl1e-3_acc_old is an 8.0B-parameter model model by hdong0. In the last 30 days it was downloaded 13 times (8 in the last 7 days), and 20 times in total.
It ranks #619,762 on the Hub by monthly downloads.
It has 0 likes.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.