thenlper / sentence-similarity updated 1 year ago

gte-base

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

Params

110 M

Context

512

Downloads 30d

541 K

Likes

131

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

Download history

daily snapshots · 10 days

543 K523 K

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	0.2 GB	0.8 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: 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): 70.128
MTEB BIOSSES (reported): 87.62669542888
MTEB ArxivClusteringP2P (reported): 48.597060136996
MTEB ArxivClusteringS2S (reported): 43.014635930021
MTEB BiorxivClusteringP2P (reported): 38.2047109268
MTEB BiorxivClusteringS2S (reported): 36.589675921476
MTEB AskUbuntuDupQuestions (reported): 74.794552169898
MTEB Banking77Classification (reported): 85.025244600982
MTEB CQADupstackAndroidRetrieval (reported): 32.411
MTEB AmazonPolarityClassification (reported): 91.765499064046
MTEB AmazonReviewsClassification (en) (reported): 48.22995586185
MTEB AmazonCounterfactualClassification (en) (reported): 68.112928880464
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 nomic-embed-text-v1.5 15.7 M multilingual-e5-small 15.6 M

Appears in

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