English BGE embedding
The record is a feature-extraction checkpoint, and the card associates BAAI/bge-base-en with English retrieval phrasing for relevant-passage search.
Open Source Model Profile · BAAI
bge-base-en
bge-base-en is a 109.48M-parameter BERT embedding model from BAAI. Its model card points users to bge-base-en-v1.5 for more reasonable similarity distribution.
- Publisher
- BAAI
- Task
- feature-extraction
- Model type
- bert
- License
- mit
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
bge-base-en is published by BAAI as a feature-extraction model. The captured configuration identifies BertModel and Safetensors metadata reports 109,482,752 parameters. According to the model card, it belongs to the BGE English embedding family and users are advised to switch to BAAI/bge-base-en-v1.5.
Recorded capabilities
Documented v1.5 successor
According to the model card, BAAI/bge-base-en-v1.5 is recommended for its more reasonable similarity distribution with the same usage method.
Commercial MIT terms
According to the model card, FlagEmbedding is MIT-licensed and released models may be used commercially free of charge; captured metadata also records mit.
Use cases in the source record
- English passage retrieval in which queries are encoded for searching relevant passages.
- Retrieve-then-rerank pipelines in which BGE embeddings return candidates for cross-encoder reranking.
Limitations and unknowns
- No context-window value was extracted from this record.
- No evaluation results specific to bge-base-en were extracted; larger BGE and reranker tables in the card concern related releases.
- Rank and performance language in the card concerns the broader BGE family and was not independently verified.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: BAAI/bge-base-en
Captured: Unknown. Processed: 2026-09-07T19:34:29.054980+00:00.
Recommend switching to newest BAAI/bge-base-en-v1.5 , which has more reasonable similarity distribution and same method of usage. FlagEmbedding Model List | FAQ | Usage | Evaluation | Train | Contact | Citation | License More details please refer to our Github: FlagEmbedding . English | 中文 FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs. ************* 🌟 Updates 🌟 ************* 10/12/2023: Release LLM-Embedder , a unified embedding model to support diverse retrieval augmen…
F001F002F003F004F005F006F007F009F010F011F015F016F018F024F025F027F028F032F036