---
license: apache-2.0
datasets:
- EleutherAI/pile
language:
- en
tags:
- tokenizer
---

A copy of Eleuther AI's [gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b), with three special tokens added to mask PII:
- `|||EMAIL_ADDRESS|||`
- `|||PHONE_NUMBER|||`
- `|||IP_ADDRESS|||`