Mini toolsBGE models
Browse all models from this model family.
to
-
BGE Code v1 is BAAIโs LLM-based code embedding model for code and text retrieval. It supports natural-language queries in English and Chinese, covers 20 programming languages, and is also designed to keep strong multilingual text-retrieval quality beyond code search.MultimodalReleased 1y ago
-
BGE VL is BAAIโs multimodal retrieval family for image-text search. It includes lightweight CLIP-based models and larger MLLM-based variants, ranging from 150M to 7.57B parameters, and is built for matching images with text or mixed image-text queries.MultimodalReleased 1y ago
-
BGE ICL is BAAIโs English embedding model with in-context learning. It is designed to improve retrieval on new tasks by adding a few-shot examples into the query, and BAAI positions it as a state-of-the-art BGE-series embedder on MTEB and AIR-Bench.TextReleased 1y ago
-
BGE Reranker v2 minicpm layerwise is BAAIโs layer-selectable multilingual reranker in the v2 family. It is built to let users choose output layers for accelerated inference, trading some depth for speed while keeping strong multilingual reranking performance.TextReleased 2y ago
-
BGE Reranker v2 gemma is BAAIโs larger multilingual reranker in the v2 family. It is designed for stronger multilingual reranking performance, with the docs highlighting good English proficiency alongside broad multilingual capability.TextReleased 2y ago
-
BGE Reranker v2 m3 is BAAIโs lightweight multilingual reranker in the v2 family. It is built for fast inference and easier deployment while keeping strong multilingual reranking capability, making it the efficiency-oriented option in the v2 lineup.TextReleased 2y ago
-
BGE M3 is BAAIโs multilingual retrieval embedding model built around three strengths: multi-functionality, multi-linguality, and multi-granularity. It supports dense retrieval, sparse retrieval, and multi-vector retrieval in one model, works across 100+ languages, and handles inputs up to 8192 tokens.TextReleased 2y ago
-
BGE Reranker base is BAAIโs lighter first-generation cross-encoder reranker for English and Chinese. It directly scores query-document relevance rather than producing embeddings, and is positioned as the faster, easier-to-deploy reranking option in the original BGE reranker family.TextReleased 2y ago
-
BGE Reranker large is BAAIโs larger first-generation cross-encoder reranker for English and Chinese. Instead of producing embeddings, it scores a query-document pair directly, making it suitable for reranking top-k retrieval results with higher accuracy after a first-pass embedder search.TextReleased 2y ago
-
BGE large v1.5 is BAAIโs top English BGE v1.5 embedding model. It is the large-scale Sep-2023 update to bge-large-en, with the docs highlighting more reasonable similarity distribution and better performance than the original version.TextReleased 2y ago
-
BGE Base v1.5 is BAAIโs mid-size English BGE v1.5 embedding model. It belongs to the Sep-2023 v1.5 update that improved retrieval behavior and similarity distribution, while keeping a balanced base-scale footprint for practical deployment.TextReleased 2y ago
-
BGE small v1.5 is BAAIโs smallest English BGE v1.5 embedding model. It keeps the compact small-model footprint while belonging to the Sep-2023 v1.5 update, which was introduced to improve retrieval without instruction tuning and to make similarity scores more reasonable.TextReleased 2y ago
-
BGE base is BAAIโs 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.TextReleased 2y ago
-
BGE small is BAAIโs smallest English BGE v1 embedding model. It is an encoder-only BERT-based text embedder designed to map text into vectors for retrieval, and is positioned as a compact model with competitive performance despite its small size.TextReleased 2y ago
-
BGE large is BAAIโs flagship English model in the original BGE v1 series. It is an encoder-only BERT-based embedding model for turning text into vectors, and the docs state it ranked first on MTEB at the time of release.TextReleased 2y ago
