Update README.md

README.md

@@ -1,4 +1,7 @@
 ---
+language:
+- en
+license: cc-by-nc-4.0
 library_name: transformers
 tags:
 - 4-bit
@@ -6,10 +9,30 @@ tags:
 - text-generation
 - autotrain_compatible
 - endpoints_compatible
+- text-generation-inference
+- transformers
+- unsloth
+- mistral
+- trl
+- sft
+- Roleplay
+- roleplay
+base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
 pipeline_tag: text-generation
 inference: false
 quantized_by: Suparious
 ---
-# 
+# Alsebay/NarumashiRTS-7B-V2-1 AWQ
 
-**UPLOAD IN PROGRESS**
+- Model creator: [Alsebay](https://huggingface.co/Alsebay)
+- Original model: [NarumashiRTS-7B-V2-1](https://huggingface.co/Alsebay/NarumashiRTS-7B-V2-1)
+
+## Model Summary
+
+> [!Important]
+> Still in experiment
+
+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 used unsafety method to save pretrain model, which could lead apply Lora layer twice to model, that make model have terrible performance. (Thanks Unsloth community told me about this :D )
+
+- **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 :)