cambridge-climb
/

CamBabyTokenizer-16384

Model card Files Files and versions Community

CamBabyTokenizer-16384 / README.md

rdiehlmartinez's picture

Update README.md

9de4c7b 12 months ago

|

history blame contribute delete

No virus

100 Bytes

metadata

language:
  - en

BPE Tokenizer Model trained on the BabyLM dataset with a vocab size of 16384.