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 +9,32 @@ tags:
 - llama
 - trl
 - sft
+- Roleplay
+- roleplay
 base_model: Sao10K/Fimbulvetr-11B-v2
 ---
+> [!Important]
+> Still in experiment
+# About this model
 
-# Uploaded  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.
 
-- **Developed by:** Alsebay
-- **License:** apache-2.0
-- **Finetuned from model :** Sao10K/Fimbulvetr-11B-v2
+This model now can handle (limited) TSF content. If you Character Card have complex plot, maybe you should try other model (maybe bigger parameter?).
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+- **Finetuned with rough translate dataset, to increase the accuracy in TSF theme, which is not quite popular. (lewd dataset)**
+- **Finetuned from model :** Sao10K/Fimbulvetr-11B-v2 . Thank Sao10K a lot :)
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## Still testing, but seem it good enough for handle information. But the logic go down a bit because the rough translate dataset. 
+GGUF version? [here is it](https://huggingface.co/Alsebay/Narumashi-RT-11B-GGUF). Although only 1 Q4_K_M available. Oh, also fp16 version.
+## 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](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)