I named my simple algorithm that generate new merging recipe near current and let user choose which is better to "learn" the best weight merging ratios with a exaggerated name "RMHF - Reinforcement Merging on Human Feedback".
https://github.com/TkskKurumi/DiffusersFastAPI/blob/main/rmhf_v2.py
描述:
recipe:
https://huggingface.co/TkskKurumi/RMHF/blob/main/RMHF-V6.2/rmhf.log
训练词语:
名称: rmhf_animev1.safetensors
大小 (KB): 2082642
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接：https://1111down.com/903759.html，转载请注明出处
