RTO-RL/Llama3-8B-RewardModel download history
RTO-RL/Llama3-8B-RewardModel is a 7.5B-parameter model model by RTO-RL. In the last 30 days it was downloaded 10 times (2 in the last 7 days), and 23 times in total.
It ranks #773,389 on the Hub by monthly downloads.
It has 0 likes.
It is a fine-tune of OpenRLHF/Llama-3-8b-sft-mixture.