Update README.md

README.md

@@ -30,6 +30,9 @@ pipeline_tag: token-classification
 ---
 
 # Piiranha-v1: Protect your personal information!
+<a target="_blank" href="https://colab.research.google.com/github/williamgao1729/piiranha-quickstart/blob/main/piiranha_quickstart.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
 Piiranha is trained to **detect 17 types** of Personally Identifiable Information (PII) across six languages. It successfully **catches 98.27% of PII** tokens, with an overall classification **accuracy of 99.44%**.
 Piiranha is especially accurate at detecting passwords, emails (100%), phone numbers, and usernames.
 
@@ -47,6 +50,7 @@ Piiranha was trained on an H100 GPU rented through the [Akash Network](https://a
 
 ## Model Description
 Piiranha is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base).
+The context length is 256 Deberta tokens. If your text is longer than that, just split it up.
 
 It achieves the following results on a test set of ~73,000 sentences containing PII:
 - Accuracy: 99.44%