Embedding Models/GTE-Qwen2-7B-instruct

GTE-Qwen2-7B-instruct by Alibaba — 3584D

Top-ranked embedding model on MTEB English and Chinese. Built on Qwen2-7B with bidirectional attention and instruction tuning.

At a glance

Modalities

Dimensions

4K

Max tokens

32K

Parameters

7B

Price / 1M tokens

Type

Dense

Output types

Single VectorMulti Vector

Language support

🌍 Multilingual support

Benchmarks

MTEB 56 70.24
CMTEB 35 72.05
MTEB FR 68.25
MTEB PL 67.86

Details

Release date 2024-06-16
License Apache 2.0
Model ID gte-qwen2-7b-instruct
Provider Alibaba

Tags

text-embeddingmultilingualinstruction-awarelong-contextopen-source