Model reference · open weights
UAE-Large is an open-weight embedding model from WhereIsAI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
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 universal English sentence embedding WhereIsAI/UAE-Large-V1 achieves SOTA on the MTEB Leaderboard with an average score of 64.64! 🧑🤝🧑 Siblings: - WhereIsAI/UAE-Code-Large-V1: This model can be used for code or GitHub issue similarity measurement. Usage 1. angleemb 1) Non-Retrieval Tasks There is no need to specify any prompts. 2) Retrieval Tasks For retrieval purposes, please use the prompt Prompts.C for query (not for document). 2. sentence transformer 3. Infinity Infinity is a MIT licensed server for OpenAI-compatible deployment. Citation If you use our pre-trained models, welcome to support us by citing our work:
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | WhereIsAI |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 335M |
| Context | 512 tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Released | 2023-12-04 |
| Popularity | 1.4M downloads / month |
| Likes | 237 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| UAE-Large-V1 | 335M | BF16 | ~0.8 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Classification | MTEB AmazonCounterfactualClassification (en) | accuracy | 75.552 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 38.264 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 69.41 |
| Classification | MTEB AmazonPolarityClassification | accuracy | 92.843 |
| Classification | MTEB AmazonPolarityClassification | ap | 89.576 |
| Classification | MTEB AmazonPolarityClassification | f1 | 92.826 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 48.292 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 47.903 |
| Retrieval | MTEB ArguAna | map_at_1 | 42.105 |
| Retrieval | MTEB ArguAna | map_at_10 | 58.181 |
| Retrieval | MTEB ArguAna | map_at_100 | 58.654 |
| Retrieval | MTEB ArguAna | map_at_1000 | 58.657 |
| Retrieval | MTEB ArguAna | map_at_3 | 54.386 |
| Retrieval | MTEB ArguAna | map_at_5 | 56.758 |
| Retrieval | MTEB ArguAna | mrr_at_1 | 42.745 |
| Retrieval | MTEB ArguAna | mrr_at_10 | 58.437 |
| Retrieval | MTEB ArguAna | mrr_at_100 | 58.895 |
| Retrieval | MTEB ArguAna | mrr_at_1000 | 58.898 |
| Retrieval | MTEB ArguAna | mrr_at_3 | 54.635 |
| Retrieval | MTEB ArguAna | mrr_at_5 | 57.0 |
| Retrieval | MTEB ArguAna | ndcg_at_1 | 42.105 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 66.15 |
| Retrieval | MTEB ArguAna | ndcg_at_100 | 68.048 |
| Retrieval | MTEB ArguAna | ndcg_at_1000 | 68.114 |
Using it via the API
Once AxForge deploys uae-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (uae-large below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"uae-large","input":"text to embed"}'
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore