v0.1.7

mvt-project/mvtv0.1.7Jan 16, 2026by chonknick

Upgrading?

AI Summary

This release introduces support for the new Voyage 4 family of embedding models, including the flagship `voyage-4-large` and lightweight variants. These models feature a 32,000 token context window and flexible dimensions via Matryoshka learning. Users can now utilize multiple quantization formats and access open-weight models under Apache 2.0.

Key Highlights

  • Added support for Voyage 4 embedding models
  • 32,000 token context window
  • Flexible dimensions via Matryoshka learning
  • Multiple quantization formats
  • Apache 2.0 open-weight model support

New Features

  • Voyage 4 embedding model 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)

Related Repositories