version "0.1.1"

Updates:

• added the tokenizer, removed the pure-python implementation
• fixed the KMer logic, still not complete though
• removed useless saved vocab & some other files

What's Changed

• created & fixed the tokenizer, not yet complete though, but still it's some progress by @shivendrra in #3

New Contributors

• @shivendrra made their first contribution in #3

Full Changelog: 0.1.0...0.1.1

version "0.1.0"

Features:

• DNA kmer-level & character-level tokenizer written in c++ & python
• vocab generator for kmer-level tokenizer
• fast & efficient, tested on vast dna dataset

Full Changelog: https://github.com/shivendrra/enigma2/commits/0.1.0