Skip to content

Latest commit

 

History

History
3 lines (2 loc) · 256 Bytes

File metadata and controls

3 lines (2 loc) · 256 Bytes

Extending the Tiktoken BPE Tokenizer with New Tokens

  • extend-tiktoken.ipynb contains optional (bonus) code to explain how we can add special tokens to a tokenizer implemented via tiktoken and how to update the LLM accordingly