Alsebay/NarumashiRTS-V2

Still in experiment

About this model

Do you know TSF, TS, TG? A lot of model don't really know about that, so I do some experiment to finetune TSF dataset.

• Finetuned with rough translate dataset, to increase the accuracy in TSF theme, which is not quite popular. (lewd dataset)
• Finetuned from model : SanjiWatsuki/Kunoichi-DPO-v2-7B . Thank SanjiWatsuki a lot :)

V2 have more epochs. You should better use V2.1.

Dataset

Dataset(all are novels):
30% skinsuit
30% possession
35% transform(shapeshift)
5% other

Thank Unsloth for good finetuning tool. This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.