TaylorAI / sentence-similarity updated 2 years ago

bge-micro-v2

Name: bge-micro-v2
Author: TaylorAI

This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Params

20 M

Context

512

Downloads 30d

1.1 M

Likes

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

Download history

daily snapshots · 10 days

1.2 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	f16	0.0 GB	0.5 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: 20 M
Tensor type: F16
Context length: 512
Vocabulary: 30,522
Layers / heads: 3 / 12
Licence: mit
First seen on the Hub: 2023-10-11
Training datasets: undisclosed
MTEB ArguAna (reported): 67.425
MTEB BIOSSES (reported): 81.727765837045
MTEB ArxivClusteringP2P (reported): 44.526922419381
MTEB ArxivClusteringS2S (reported): 33.245710292774
MTEB BiorxivClusteringP2P (reported): 36.109308463096
MTEB BiorxivClusteringS2S (reported): 28.060482123172
MTEB AskUbuntuDupQuestions (reported): 71.943784900849
MTEB Banking77Classification (reported): 81.098938363105
MTEB CQADupstackAndroidRetrieval (reported): 28.234
MTEB AmazonPolarityClassification (reported): 79.653196154338
MTEB AmazonReviewsClassification (en) (reported): 37.024519885497
MTEB AmazonCounterfactualClassification (en) (reported): 61.311811871119
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 paraphrase-MiniLM-L6-v2 2.8 M paraphrase-MiniLM-L3-v2 2.6 M

Appears in

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