Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · WhereIsAI

UAE-Large-V1

UAE-Large-V1 is a 335.1M-parameter BERT feature-extraction model from WhereIsAI. Its model card titles it Universal AnglE Embedding and captured metadata records an MIT license.

Publisher
WhereIsAI
Task
feature-extraction
Model type
bert
License
mit
Library
sentence-transformers
Publication status
Approved for indexing

Model overview

WhereIsAI publishes UAE-Large-V1 as a sentence-transformers feature-extraction model. Captured config identifies BertModel with a bert model type, and Safetensors metadata reports 335,141,888 parameters. Card data records mit. Hub tags include onnx, openvino, mteb, sentence_embedding, transformers.js, en, and arxiv:2309.12871. The model card points to AnglE-optimized text embeddings work and ACL24 Angle-optimized Embeddings for STS.

Recorded capabilities

About 335.1M parameters

Safetensors metadata reports 335,141,888 parameters, or about 335.1M.

MIT licensing

Captured metadata records an mit license. The model card also says the checkpoint is licensed under MIT.

AnglE embedding card

The model card titles the work Universal AnglE Embedding and links AnglE training/inference documentation.

CLS pooling example

The captured usage snippet loads AnglE.from_pretrained with pooling_strategy='cls' and normalize_embedding=True.

Use cases in the source record

  • Sentence embedding and cosine-similarity comparison using the card's AnglE CLS-pooling example.
  • Retrieval workflows where the model card says to apply Prompts.C to the query and not the document.

Limitations and unknowns

  • No evaluation scores were extracted from this record, despite an mteb hub tag.
  • No embedding-dimension value was extracted as a structured field.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • AnglE usage details, retrieval prompt guidance, and paper citations come from the publisher model card and have not been independently verified by Ethen.

Source and provenance

Source: WhereIsAI/UAE-Large-V1

Captured: Unknown. Processed: 2026-09-07T19:34:38.846512+00:00.

Universal AnglE Embedding 📢 WhereIsAI/UAE-Large-V1 is licensed under MIT. Feel free to use it in any scenario. If you use it for academic papers, you could cite us via 👉 citation info . 🤝 Follow us on: GitHub: https://github.com/SeanLee97/AnglE . Preprint Paper: AnglE-optimized Text Embeddings Conference Paper: AoE: Angle-optimized Embeddings for Semantic Textual Similarity (ACL24) 📘 Documentation : https://angle.readthedocs.io/en/latest/index.html Welcome to using AnglE to train and infer powerful sentence embeddings. 🏆 Achievements 📅 May 16, 2024 | AnglE's paper is accepted by ACL 2024 Main Conference 📅 Dec 4, 2023 | 🔥 Our…

F001F002F003F004F005F006F007F008F009F010F011F014F015F016