e5-small-v2
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
30 M
Context
512
Downloads 30d
552 K
Likes
125
Download history
daily snapshots · 55 days
▲ 185 K in the last 30 days (25.1%)
724 K513 K
Aug 22Sep 1Sep 11Sep 20
790 K513 K
Jul 28Aug 15Sep 2Sep 20
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 | 0.1 GB | 0.7 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
- 30 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)
- 51.991
- MTEB BIOSSES (reported)
- 78.293952655523
- MTEB ArxivClusteringP2P (reported)
- 42.116951744707
- MTEB ArxivClusteringS2S (reported)
- 34.795537201071
- MTEB BiorxivClusteringP2P (reported)
- 35.885411371376
- MTEB BiorxivClusteringS2S (reported)
- 30.052056852744
- MTEB AskUbuntuDupQuestions (reported)
- 71.564107637515
- MTEB Banking77Classification (reported)
- 81.55779952377
- MTEB CQADupstackAndroidRetrieval (reported)
- 30.294
- MTEB AmazonPolarityClassification (reported)
- 91.242975214257
- MTEB AmazonReviewsClassification (en) (reported)
- 45.080588703812
- MTEB AmazonCounterfactualClassification (en) (reported)
- 71.864659463986
- Added to our catalog
- 2026-07-28
Compare with any sentence-similarity model