Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models

Autor:	Merrick, Luke, Xu, Danmei, Nuti, Gaurav, Campos, Daniel
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Information Retrieval
Druh dokumentu:	Working Paper
Popis:	This report describes the training dataset creation and recipe behind the family of \texttt{arctic-embed} text embedding models (a set of five models ranging from 22 to 334 million parameters with weights open-sourced under an Apache-2 license). At the time of their release, each model achieved state-of-the-art retrieval accuracy for models of their size on the MTEB Retrieval leaderboard, with the largest model, arctic-embed-l outperforming closed source embedding models such as Cohere's embed-v3 and Open AI's text-embed-3-large. In addition to the details of our training recipe, we have provided several informative ablation studies, which we believe are the cause of our model performance. Comment: 17 pages, 11 Figures, 9 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.05374 Zobrazit plný text záznamu View this record from Arxiv