hdong0/deepseek-Llama-8B-Open-R1-GRPO_deepscaler_1000steps_lr1e-6_kl1e-3_acc download history

hdong0/deepseek-Llama-8B-Open-R1-GRPO_deepscaler_1000steps_lr1e-6_kl1e-3_acc is an 8.0B-parameter text generation model by hdong0. In the last 30 days it was downloaded 20 times (11 in the last 7 days), and 59 times in total.

It ranks #413,292 on the Hub by monthly downloads and #124,765 among text generation models.

It has 0 likes.

It is a fine-tune of deepseek-ai/DeepSeek-R1-Distill-Llama-8B.

Open hdong0/deepseek-Llama-8B-Open-R1-GRPO_deepscaler_1000steps_lr1e-6_kl1e-3_acc on Hugging Face

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