Alibaba-NLP / sentence-similarity updated 1 year ago

gte-Qwen2-1.5B-instruct

gte-Qwen2-1.5B-instruct is the latest model in the gte (General Text Embedding) model family. The model is built on Qwen2-1.5B LLM model and use the same training data and strategies as the gte-Qwen2-7B-instruct model.

Params
1.8 B
Context
131,072
Downloads 30d
1.2 M
Likes
236
Commercial use: allowed apache-2.0 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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f32 7.1 GB 8.6 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 128K ctx 7.1 GB 12.6 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
Qwen2ForCausalLM
Parameters
1.8 B
Tensor type
F32
Context length
131,072
Vocabulary
151,646
Layers / heads
28 / 12
Licence
apache-2.0
First seen on the Hub
2024-06-29
Training datasets
undisclosed
MTEB ArguAna (reported)
84.851
MTEB BIOSSES (reported)
80.574125092726
MTEB ArxivClusteringP2P (reported)
50.511868162026
MTEB ArxivClusteringS2S (reported)
45.007803189284
MTEB BiorxivClusteringP2P (reported)
43.207546089349
MTEB BiorxivClusteringS2S (reported)
38.818037697336
MTEB AskUbuntuDupQuestions (reported)
77.661588180979
MTEB Banking77Classification (reported)
87.253073224433
MTEB CQADupstackAndroidRetrieval (reported)
35.423
MTEB AmazonPolarityClassification (reported)
96.609425969406
MTEB AmazonReviewsClassification (en) (reported)
54.905534802949
MTEB AmazonCounterfactualClassification (en) (reported)
78.504165990512
Added to our catalog
2026-07-28