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 Foundation models & chat 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. GTE ModernColBERT is open source under the MIT license. GTE ModernColBERT is available on the web, the command line, and API.
LightOn AI builds and maintains GTE ModernColBERT, and the product first shipped in 2024. Development happens publicly on GitHub with 875 stars and 15 commits in the last 90 days. Key capabilities include colBERT, Sentence Similarity, and embedding.
Latest indexed changes and source events
lightonai/GTE-ModernColBERT-v1 verified by the PulseGate indexer
Other apps tracked under the same category.
