GTE-ModernColBERT-v1 is a ColBERT-style embedding model based on ModernBERT, developed by LightOn AI. It produces token-level embeddings optimized for late-interaction retrieval, enabling highly accurate semantic search over documents. The model supports both query and document encoding and is compatible with the PyLate and sentence-transformers libraries.
GTE ModernColBERT sits in PulseGate's Embeddings & retrieval category. It focuses on generating high-quality late-interaction embeddings for semantic search and retrieval tasks. It is built as an open-source project for developers building search and RAG systems. The project is open source (MIT). GTE ModernColBERT is available on the web, the command line, and API.
Behind GTE ModernColBERT is LightOn AI, and it first shipped in 2024. The project is developed in the open on GitHub with 875 stars and 15 commits in the last 90 days. Among its 3 catalogued features are colBERT, Sentence Similarity, and embedding.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do