Alibaba-NLP / sentence-similarity updated 1 year ago

gte-large-en-v1.5

We introduce gte-v1.5 series, upgraded gte embeddings that support the context length of up to 8192, while further enhancing model performance. The models are built upon the transformer++ encoder backbone (BERT + RoPE + GLU).

Params
430 M
Context
8,192
Downloads 30d
1.7 M
Likes
238
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
1.7 M1.7 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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f32 1.7 GB 2.5 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
NewModel
Parameters
430 M
Tensor type
F32
Context length
8,192
Vocabulary
30,528
Layers / heads
24 / 16
Licence
apache-2.0
First seen on the Hub
2024-04-20
Training datasets
allenai/c4
MTEB ArguAna (reported)
87.98
MTEB BIOSSES (reported)
85.117602112908
MTEB ArxivClusteringP2P (reported)
48.467787861077
MTEB ArxivClusteringS2S (reported)
43.391983919143
MTEB BiorxivClusteringP2P (reported)
40.577932830194
MTEB BiorxivClusteringS2S (reported)
37.944256238651
MTEB AskUbuntuDupQuestions (reported)
75.933144264169
MTEB Banking77Classification (reported)
87.291329459996
MTEB CQADupstackAndroidRetrieval (reported)
32.978
MTEB AmazonPolarityClassification (reported)
93.958481377169
MTEB AmazonReviewsClassification (en) (reported)
53.801223340128
MTEB AmazonCounterfactualClassification (en) (reported)
66.712703108839
Added to our catalog
2026-07-28