Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 language:
 - en
-license: apache-2.0
+license: cc-by-nc-4.0
 tags:
 - text-generation-inference
 - transformers
@@ -9,15 +9,29 @@ tags:
 - mistral
 - trl
 - sft
+- Roleplay
+- roleplay
 base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
 ---
+> [!Important]
+> Still in experiment
+# About this model
 
-# Uploaded  model
+Remake [version 2](https://huggingface.co/Alsebay/NarumashiRTS-V2) with safetensor format, more safety and stable method, nothing change too much (base on the model hash). But to be real, in the previous version 2, I have use unsafety method to save pretrain model, which could lead apply Lora layer twice to model, that make model have terrible performance. 
 
-- **Developed by:** Alsebay
-- **License:** apache-2.0
-- **Finetuned from model :** SanjiWatsuki/Kunoichi-DPO-v2-7B
+- **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 :)
 
-This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## V2 have more epochs.
+## Dataset
+```
+Dataset(all are novels):
+30% skinsuit
+30% possession
+35% transform(shapeshift)
+5% other
+```
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+# Thank Unsloth for good finetuning tool. This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)