Popular repositories Loading

1. tokenmonster tokenmonster Public

   Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript

   Go 532 19

2. capcode capcode Public

   Lossless normalization of uppercase characters

   Go 9

3. branchless branchless Public

   Go branchless helper functions for ints

   Go 3 1

4. slmqa slmqa Public

   Small language model QA quality eval benchmark

   Python 3

5. pansearch pansearch Public

   Forked from AlasdairF/BinSearch

   Backend for TokenMonster

   Go 1

6. norm norm Public

   Basic text normalization

   Go 1