High-performance BPE tokenizer editor for HuggingFace tokenizer.json files
A high-performance Turkish tokenizer based on linguistic rules and BPE, written in Rust.
A comprehensive knowledge distillation training framework for transformer models
Clone and prune transformer models with new tokenizers
Anthropic, PBC
Visionary sponsor
Bloomberg
Visionary sponsor
Hudson River Trading
Visionary sponsor
Meta
Visionary sponsor
NVIDIA
Visionary sponsor
Microsoft
Sustainability sponsor
Depot
Continuous Integration
AWS
Cloud computing and Security Sponsor
Datadog
Monitoring
Fastly
CDN
Google
Download Analytics
Sentry
Error logging
StatusPage
Status page