thenlper / sentence-similarity updated 1 year ago

gte-large

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

Params

340 M

Context

512

Downloads 30d

633 K

Likes

307

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

Download history

daily snapshots · 55 days

▲ 171 K in the last 30 days (21.3%)

898 K633 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	0.7 GB	1.3 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: 340 M
Tensor type: F16
Context length: 512
Vocabulary: 30,522
Layers / heads: 24 / 16
Licence: mit
First seen on the Hub: 2023-07-27
Training datasets: undisclosed
MTEB ArguAna (reported): 70.555
MTEB BIOSSES (reported): 88.211648516469
MTEB ArxivClusteringP2P (reported): 48.619246083417
MTEB ArxivClusteringS2S (reported): 43.357406766469
MTEB BiorxivClusteringP2P (reported): 39.105105197395
MTEB BiorxivClusteringS2S (reported): 36.846899602644
MTEB AskUbuntuDupQuestions (reported): 76.155960075628
MTEB Banking77Classification (reported): 86.015555976818
MTEB CQADupstackAndroidRetrieval (reported): 32.8
MTEB AmazonPolarityClassification (reported): 92.511121694318
MTEB AmazonReviewsClassification (en) (reported): 48.44785682573
MTEB AmazonCounterfactualClassification (en) (reported): 66.236843539509
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 paraphrase-multilingual-mpnet-base-v2 9.9 M multilingual-e5-base 7.6 M