qdrant/quaterion
A framework built on PyTorch Lightning for fine-tuning similarity learning models at high speed with caching optimizations.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
Quaterion is a Python framework designed to fine-tune pre-trained models for similarity learning tasks such as semantic search, recommendation systems, anomaly detection, and matching engines. It leverages PyTorch Lightning for distributed training, includes built-in caching to enable fast iteration even on limited hardware, and provides customizable head layers to specialize models on custom datasets with minimal data requirements.