thenlper / sentence-similarity updated 1 year ago

gte-small

General Text Embeddings (GTE) model. Towards General Text Embeddings with Multi-stage Contrastive Learning

Params

30 M

Context

512

Downloads 30d

1.1 M

Likes

191

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

Download history

daily snapshots · 55 days

▲ 83 K in the last 30 days (8.4%)

1.1 M618 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	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: BertModel
Parameters: 30 M
Tensor type: F16
Context length: 512
Vocabulary: 30,522
Layers / heads: 12 / 12
Licence: mit
First seen on the Hub: 2023-07-27
Training datasets: undisclosed
MTEB ArguAna (reported): 68.848
MTEB BIOSSES (reported): 88.009234265769
MTEB ArxivClusteringP2P (reported): 47.901780781977
MTEB ArxivClusteringS2S (reported): 40.257283934319
MTEB BiorxivClusteringP2P (reported): 38.365747692594
MTEB BiorxivClusteringS2S (reported): 35.485703316529
MTEB AskUbuntuDupQuestions (reported): 75.241392956074
MTEB Banking77Classification (reported): 84.014850173022
MTEB CQADupstackAndroidRetrieval (reported): 30.261
MTEB AmazonPolarityClassification (reported): 91.80367382707
MTEB AmazonReviewsClassification (en) (reported): 47.449066567472
MTEB AmazonCounterfactualClassification (en) (reported): 67.32056515392
Added to our catalog: 2026-07-28

Compare with any sentence-similarity model

Popular comparisons

all-MiniLM-L6-v2 254.1 M paraphrase-multilingual-MiniLM-L12-v2 45.9 M bge-m3 38.0 M all-mpnet-base-v2 22.6 M nomic-embed-text-v1.5 14.7 M all-MiniLM-L12-v2 4.2 M