intfloat / sentence-similarity updated 1 year ago

e5-base-v2

Name: e5-base-v2
Author: intfloat

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022

Params

110 M

Context

512

Downloads 30d

1.1 M

Likes

156

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

Download history

daily snapshots · 10 days

1.3 M1.1 M

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	0.4 GB	1.0 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: 110 M
Tensor type: F32
Context length: 512
Vocabulary: 30,522
Layers / heads: 12 / 12
Licence: mit
First seen on the Hub: 2023-05-19
Training datasets: undisclosed
MTEB ArguAna (reported): 55.761
MTEB BIOSSES (reported): 81.804273604422
MTEB ArxivClusteringP2P (reported): 46.103124014402
MTEB ArxivClusteringS2S (reported): 39.672753260954
MTEB BiorxivClusteringP2P (reported): 37.495115019668
MTEB BiorxivClusteringS2S (reported): 32.724792944167
MTEB AskUbuntuDupQuestions (reported): 72.768324319571
MTEB Banking77Classification (reported): 83.452986793609
MTEB CQADupstackAndroidRetrieval (reported): 32.361
MTEB AmazonPolarityClassification (reported): 92.803909119707
MTEB AmazonReviewsClassification (en) (reported): 46.11544975436
MTEB AmazonCounterfactualClassification (en) (reported): 72.120406282666
Added to our catalog: 2026-07-28

Compare with

all-MiniLM-L6-v2 257.8 M paraphrase-multilingual-MiniLM-L12-v2 59.4 M bge-m3 35.0 M all-mpnet-base-v2 25.2 M nomic-embed-text-v1.5 15.7 M multilingual-e5-small 15.6 M

Appears in

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