e5-base-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
110 M
Context
512
Downloads 30d
851 K
Likes
157
Download history
daily snapshots · 55 days
▲ 389 K in the last 30 days (31.4%)
1.3 M851 K
Aug 22Sep 1Sep 11Sep 20
1.3 M851 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 | 0.4 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 any sentence-similarity model