jinaai / feature-extraction updated 1 year ago

jina-embeddings-v2-small-en

The easiest way to starting using jina-embeddings-v2-small-en is to use Jina AI's Embedding API.

Params

30 M

Context

8,192

Downloads 30d

1.0 M

Likes

141

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.3 M1.0 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	f16	0.1 GB	0.6 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: JinaBertForMaskedLM
Parameters: 30 M
Tensor type: F16
Context length: 8,192
Vocabulary: 30,528
Layers / heads: 4 / 8
Licence: apache-2.0
First seen on the Hub: 2023-09-27
Training datasets: jinaai/negation-dataset
MTEB ArguAna (reported): 56.757
MTEB BIOSSES (reported): 80.125922109033
MTEB ArxivClusteringP2P (reported): 44.02420878392
MTEB ArxivClusteringS2S (reported): 35.161368560003
MTEB BiorxivClusteringP2P (reported): 35.572385960057
MTEB BiorxivClusteringS2S (reported): 29.066444306197
MTEB AskUbuntuDupQuestions (reported): 73.072154069384
MTEB Banking77Classification (reported): 77.349509135406
MTEB CQADupstackAndroidRetrieval (reported): 31.891
MTEB AmazonPolarityClassification (reported): 82.833578027227
MTEB AmazonReviewsClassification (en) (reported): 39.209432767163
MTEB AmazonCounterfactualClassification (en) (reported): 65.385368553555
Added to our catalog: 2026-07-28

Compare with

bge-small-en-v1.5 72.4 M bge-base-en-v1.5 10.0 M bge-small-zh-v1.5 4.8 M granite-embedding-small-english-r2 3.8 M all-MiniLM-L6-v2 2.9 M bge-base-en-v1.5 2.2 M

Appears in

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