neuron-core/tokenizer

High-Performance Tokenizer implementation in PHP.

29
/ 100
Experimental

It provides a Byte-Pair Encoding (BPE) tokenizer, loading pre-trained vocabulary and merge files (e.g., from Hugging Face's GPT-2 datasets). The implementation emphasizes performance through a cache strategy and priority queue for efficient tokenization, targeting PHP applications requiring NLP capabilities.

No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 9 / 25
Community 10 / 25

How are scores calculated?

Stars

6

Forks

1

Language

PHP

License

MIT

Last pushed

Oct 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/neuron-core/tokenizer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.