Update README.md

README.md

@@ -20,14 +20,16 @@ The original foundation model was finetuned on a balanced dataset created by uni
 - [![Generic badge](https://img.shields.io/badge/Dataset-DefamationJapaneseTwitter-red.svg)](https://huggingface.co/datasets/kubota/defamation-japanese-twitter) 
 - `DefamationJapaneseYouTube` : TBA 
 
-<b>Labels</b>: 
-0 -> "中傷性のない発言";
-1 -> "脅迫的な発言";
-2 -> "侮蔑的な発言";
+<b>Labels</b>:\
+0 -> "中傷性のない発言"\
+1 -> "脅迫的な発言"\
+2 -> "侮蔑的な発言"\
 3"-> "名誉を低下させる発言"
 
 ## Example Pipeline
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/kubotaissei/defamation_japanese_twitter/blob/master/src/example.ipynb)
 ```python
+# !pip install transformers==4.26 sentencepiece
 from transformers import pipeline
 pipe = pipeline(model="kubota/luke-large-defamation-detection-japanese")
 pipe("あの人は殺人を犯した犯罪者らしい")