更新了光辉版本for illustrious is Updated新的こたろう（Kot_Rou020）style是为JRU2（<a target="_blank" rel="ugc" href="https://civarchive.com/models/303060">https://civarchive.com/models/303060</a>）训练的，在Kohaku-XL Epsilon（<a target="_blank" rel="ugc" href="https://civarchive.com/models/399873/kohaku-xl-epsilon">https://civarchive.com/models/399873/kohaku-xl-epsilon</a>）上也有不错的效果 The new こたろう（Kot_Rou020）, trained for JRU2 (<a target="_blank" rel="ugc" href="https://civarchive.com/models/303060">https://civarchive.com/models/303060</a>), also performs well on Kohaku-XL Epsilon (<a target="_blank" rel="ugc" href="https://civarchive.com/models/399873/kohaku-xl-epsilon">https://civarchive.com/models/399873/kohaku-xl-epsilon</a>).以下是上次更新的内容XL版本的こたろう（Kot_Rou020）style，使用琥珀昨天晚上发布的Kohaku-XL gamma（<a target="_blank" rel="ugc" href="https://civarchive.com/models/270291">https://civarchive.com/models/270291</a>）训练的，这个模型很适合作为训练的底模。之后我可能会把以前训练过的1.5版本的画风lora升级成xl版本的。训练集和之前一样来自于こたろう（Kot_Rou020） The XL version of こたろう（Kot_Rou020）style, trained using Kohaku-XL gamma released by Kohaku last night (<a target="_blank" rel="ugc" href="https://civarchive.com/models/270291">https://civarchive.com/models/270291</a>), is very suitable as a base model for training. Later, I might upgrade the 1.5 version of the style Lora I've trained before to the XL version.The training set, just like before, comes from こたろう（Kot_Rou020）.

こたろう（Kot_Rou020）style

谁能教教我怎么改变gpt4的文风啊，写出来的小说有一种质朴的美（）

Files with SHA256: 4f891ae104aef43557fd808c1c9798a987d867d3dd6817700d6d4c290463b348