GitLab Transcend - Intelligent orchestration
Mini toolsBGE base
BGE base is the middle English model in the original BGE v1 family released in Aug-2023. According to the BGE documentation, it is an encoder-only BERT-based embedding model with 109M parameters and a 438 MB model size. It is designed for dense retrieval and general text embedding, and is specifically described as a base-scale model with capability similar to bge-large-en, making it a balance between footprint and retrieval quality.
Text
Gen 7
Overview
BGE base is BAAI’s mid-size English BGE v1 embedding model. It is an encoder-only BERT-based text embedder for mapping text into vectors, and the docs position it as a base-scale model with ability similar to the larger bge-large-en.
About Beijing Academy of Artificial Intelligence (BAAI)
Beijing Academy of Artificial Intelligence (BAAI), also known as Zhiyuan Institute, is a Chinese non-profit AI research laboratory established in November 2018. BAAI conducts fundamental AI research, develops open-source models (including WuDao, BGE embeddings, Emu, and RoboBrain), and fosters collaboration between academia and industry. Known for creating the BGE (BAAI General Embedding) series of embedding models used in RAG systems worldwide.
View Company ProfileTools using BGE base
No tools found for this model yet.
Last updated: April 16, 2026
