Skip to content
#

tokenizer-engineering

Here is 1 public repository matching this topic...

HTGM.2 is a Hindi-first BPE tokenizer trained on ~41GB corpus using streaming architecture for scalable Hindi LLMs, Devanagari NLP, and low-memory tokenizer engineering.

  • Updated May 17, 2026
  • Python

Add this topic to your repo

To associate your repository with the tokenizer-engineering topic, visit your repo's landing page and select "manage topics."

Learn more