Update README.md

README.md

@@ -31,8 +31,7 @@ Training is done using Japanese, English, and Chinese (traditional characters) a
 The output language of the thought process is Japanese only.
 I think it will probably work with other languages that are supported by qwen 2.5.
 
-
-### prompt template
+### prompt template/プロンプトテンプレート
 
 #### Input prompt template/入力テンプレート
 
@@ -98,16 +97,22 @@ masterpiece, best quality, highresなどの品質に関連するタグは後工
 詳細はSample Scriptを確認してください  
 Please check Sample Script for details.  
 
-
 ### Sample Script
 
-[Google Colabのサンプル](https://github.com/webbigdata-jp/python_sample/blob/main/FanFic_Illustrator_demo.ipynb)
+[Google Colabのサンプル](https://github.com/webbigdata-jp/python_sample/blob/main/FanFic_Illustrator_demo.ipynb)  
 [Sample Colab Script](https://github.com/webbigdata-jp/python_sample/blob/main/FanFic_Illustrator_demo.ipynb)
 
 
+### Acknowledgements/謝辞
+We would like to thank the following people for providing related models/methods/tools.  
+以下の関連モデル/手法/ツールを提供してくださった皆さんに感謝します。
+- Base Model: [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
+- Image Generation model: [cagliostrolab/animagine-xl-4.0](https://huggingface.co/cagliostrolab/animagine-xl-4.0)
+- Training Methods: (Deepseek GRPO)[https://arxiv.org/abs/2402.03300]
+- Traing script: [Unsloth](https://huggingface.co/unsloth).
+
 
 - **Developed by:** webbigdata
 - **Model type:** text generation
 - **Language(s) (NLP):** Japanese, English
-- **Finetuned from model [optional]:** Qwen 2.5 3B Instruct
-
+- **Finetuned from model [optional]:** Qwen 2.5 3B Instruct