English embedding with documented usage
According to the model card, bge models are usable with FlagEmbedding, Sentence-Transformers, Langchain, or Transformers, with CLS pooling documented for Transformers.
Open Source Model Profile · BAAI
bge-large-en
bge-large-en is a BAAI 335M-parameter BERT embedding model for English feature extraction. The record carries MIT licensing.
- Publisher
- BAAI
- Task
- feature-extraction
- Model type
- bert
- License
- mit
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
bge-large-en is published by BAAI as an English feature-extraction embedding model. The captured configuration identifies BertModel with model type bert, and Safetensors metadata reports 335,142,400 parameters. According to the model card, users are advised to switch to bge-large-en-v1.5 under MIT licensing.
Recorded capabilities
Retrieval plus rerank pattern
The model card describes retrieving top documents with a bge embedding model and reranking them with a bge reranker.
Contrastive training context
According to the model card, bge pre-training uses retromae on large-scale pairs data, followed by contrastive fine-tuning before similarity use.
MIT record
The hub record carries MIT licensing, and the model card describes commercial use free of charge.
Use cases in the source record
- English passage retrieval and similarity workflows using the card's documented FlagEmbedding, Sentence-Transformers, Langchain, or Transformers paths.
- Retrieve-and-rerank workflows combining a bge embedding model with a bge cross-encoder reranker for top-k documents.
Limitations and unknowns
- No context-window, embedding dimension, hardware requirement, or quantization detail was extracted.
- No independent Ethen evaluation results were extracted.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Rank and benchmark claims come from the publisher model card and were not independently verified by Ethen.
Source and provenance
Source: BAAI/bge-large-en
Captured: Unknown. Processed: 2026-09-07T19:34:29.493063+00:00.
Recommend switching to newest BAAI/bge-large-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 augme…
F001F002F003F004F005F006F007F010F011F015F016F024F025F026F028F029F030F031F032F033F035F036