Top-tier 7B retrieval embedder from Linq AI Research using refined synthetic data and hard-negative mining.
Access model weights, configuration files, and documentation.
See which devices can run this model and at what quality level.
A 7B text embedding model built on top of E5-Mistral-7B-Instruct and Mistral-7B-v0.1 by Linq AI Research, focused on advanced data refinement: sophisticated data crafting, filtering, and task-specific hard-negative mining via teacher models on both benchmark and synthetic datasets. Topped MTEB Retrieval among publicly available models at its May 2024 release with a 60.2 score.
View on Hugging Face