sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-easy-AT-1 download history
sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-easy-AT-1 is an 8.0B-parameter text generation model by sleeepeer. In the last 30 days it was downloaded 7 times (7 in the last 7 days), and 50 times in total.
It ranks #1,034,967 on the Hub by monthly downloads and #373,213 among text generation models.
It has 0 likes.
It is a fine-tune of sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-alpaca_combine_100_no_KL-checkpoint-300.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.