WhereIsAI / feature-extraction updated 1 year ago

UAE-Large-V1

Name: UAE-Large-V1
Author: WhereIsAI

📢 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.

Params

340 M

Context

512

Downloads 30d

928 K

Likes

237

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

928 K688 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	1.3 GB	2.0 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: BertModel
Parameters: 340 M
Tensor type: F32
Context length: 512
Vocabulary: 30,522
Layers / heads: 24 / 16
Licence: mit
First seen on the Hub: 2023-12-04
Training datasets: undisclosed
MTEB ArguAna (reported): 80.797
MTEB BIOSSES (reported): 86.210398097344
MTEB ArxivClusteringP2P (reported): 49.025807591542
MTEB ArxivClusteringS2S (reported): 43.093601280164
MTEB BiorxivClusteringP2P (reported): 39.375016875004
MTEB BiorxivClusteringS2S (reported): 37.234014051559
MTEB AskUbuntuDupQuestions (reported): 77.09547992789
MTEB Banking77Classification (reported): 87.681093819435
MTEB CQADupstackAndroidRetrieval (reported): 30.232
MTEB AmazonPolarityClassification (reported): 92.825907343378
MTEB AmazonReviewsClassification (en) (reported): 47.902578160328
MTEB AmazonCounterfactualClassification (en) (reported): 69.409779347698
Added to our catalog: 2026-07-28

Compare with

bge-small-en-v1.5 72.4 M bge-large-en-v1.5 13.1 M bge-base-en-v1.5 10.0 M Qwen3-Embedding-0.6B 9.8 M multilingual-e5-large 7.5 M mxbai-embed-large-v1 4.9 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB