ASTERIZER/Ezaris-Tokenizer download history

ASTERIZER/Ezaris-Tokenizer is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,023 times (142 in the last 7 days), and 1,451 times in total. It ranks #18,984 among datasets by monthly downloads.

Ezaris Tokenizer — Program & Corpus The single home of the Asterizer tokenizer for the Ezaris program: one byte-level BPE tokenizer, frozen once and reused across every ASTERIZER model from 100M → 1T params. South-Indian-first (Kannada / Tamil / Telugu / Malayalam), plus code, math, a

Open ASTERIZER/Ezaris-Tokenizer on Hugging Face