CoolFace
Modelpublic

miguelcsx/causal-focus-bbpe16k-tokenizer

sourceHugging Faceotherupdated 3mo agoView on Hugging Face
0likes
Model Card

CausalFocus BBPE16K Tokenizer

Tokenizer-only repository for CausalFocus-GPTBERT-D256-BBPE16K.

  • —family: byte-level BPE
  • —vocab size: 16000
  • —max sequence length used by release training: 512
  • —source corpus: miguelcsx/babylm-corpus-cleaned