v0.1.7

BigBodyCobain/Shadowbrokerv0.1.7Jan 16, 2026by chonknick

AI Summary

This release introduces support for the new Voyage 4 family of embedding models, providing options from lightweight to flagship sizes. It adds support for advanced features like 32,000 token context windows and flexible dimensions.

Key Highlights

Added Voyage 4 embedding model support (large, mid, lite, nano)
Models support 32,000 token context windows
Flexible dimensions via Matryoshka learning
Support for multiple quantization formats

New Features

Voyage 4 embedding model integration
32k token context support
Matryoshka flexible dimensions
Multi-format quantization support

Full Release Notes

## What's New

- Added support for Voyage 4 embedding models:
  - `voyage-4-large` - Flagship MoE model, #1 on MTEB (78.26)
  - `voyage-4` - Mid-sized balanced model
  - `voyage-4-lite` - Lightweight model, #9 on MTEB (73.29)
  - `voyage-4-nano` - Open-weight model (Apache 2.0)

All Voyage 4 models support:
- 32,000 token context
- Flexible dimensions (2048/1024/512/256) via Matryoshka learning
- Multiple quantization formats (float, int8, binary)