RLAIF/grpo_thinking_ultrafeedback-original_32_64_4_3e-3_2e-7_step-120_1.7B download history

RLAIF/grpo_thinking_ultrafeedback-original_32_64_4_3e-3_2e-7_step-120_1.7B is a 2.0B-parameter model model by RLAIF. In the last 30 days it was downloaded 3 times (1 in the last 7 days), and 13 times in total.

It ranks #1,343,836 on the Hub by monthly downloads.

It has 0 likes.

Open RLAIF/grpo_thinking_ultrafeedback-original_32_64_4_3e-3_2e-7_step-120_1.7B on Hugging Face

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