uniqtoken
https://github.com/umran666/uniqtoken
Python
High-precision, zero-dependency Byte-Fallback Unigram tokenizer with dual-offset tracking, arithmetic isolation, and multilingual Unicode protection.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to uniqtoken
Help out
- Issues
- perf: add performance regression gate to CI (#106)
- perf: add performance regression gate to CI
- perf: prototype FastBPE-inspired incremental merge engine
- research: differential verification for ReferenceMergeEngine vs FastMergeEngine
- perf: benchmark FastMergeEngine against current SuperBPE merge path
- perf: optimize FastMergeEngine pair-queue and invalidation strategy
- perf: reduce FastMergeEngine memory allocations and copies
- research: validate FastMergeEngine with full SuperBPE/CEM semantics
- research/perf: decide whether FastMergeEngine replaces the current merge core
- Docs
- Python not yet supported