nomic-ai/contrastors
PyTorch-based toolkit for training contrastive embedding models for retrieval, multimodal, and RAG applications.
Not currently ranked — collecting fresh signals.
star history
Contrastors is a contrastive learning library enabling researchers and engineers to train embedding models efficiently. It supports multi-GPU training, large batch sizes via GradCache, and builds on Flash Attention for speed. The toolkit supports CLIP and LiT-style contrastive learning, Matryoshka Representation Learning for flexible embedding dimensions, and multimodal training with ViT models alongside text encoders. It includes pretrained embedding models like Nomic Embed used in production RAG systems.
Frequently asked
- What is nomic-ai/contrastors?
- PyTorch-based toolkit for training contrastive embedding models for retrieval, multimodal, and RAG applications.
- Is contrastors open source?
- Yes — nomic-ai/contrastors is open source, released under the Apache-2.0 license.
- What language is contrastors written in?
- nomic-ai/contrastors is primarily written in Python.
- How popular is contrastors?
- nomic-ai/contrastors has 798 stars on GitHub.
- Where can I find contrastors?
- nomic-ai/contrastors is on GitHub at https://github.com/nomic-ai/contrastors.