2024/02/19:
新增PornMaster-Amateur&DPO-V1版本，重新调整模型合并的比例并且增加DPO模型的合并。的合并。DPO论文。
Added PornMaster-Amateur&DPO-V1 version, re-adjusted the proportion of model merging and increased the merging of DPO model. DPO papers.
搭配DPO (Direct Preference Optimization) 的Lora使用，可以提升提示词的准确性。
Used with Lora of DPO (Direct Preference Optimization), the accuracy of prompt words can be improved.