← Back to AI Models

GTE-Qwen2-7B-instruct

High-performance embedding model based on Qwen2

Overview

High-performance embedding model based on Qwen2 The model has 7B parameters. It is an open-weight model released under the Apache 2.0 licence.

Key Capabilities

Embeddings — suited for tasks requiring embeddings proficiency
Long Context — suited for tasks requiring long context proficiency
Multilingual — suited for tasks requiring multilingual proficiency

Recommended Use Cases

Long Document Rag
Multilingual Search
High Quality

Technical Specifications

Context Window: 33K tokens
Parameters: 7B
Open Weight: Yes
Licence: Apache 2.0
Release Date: June 22, 2024

Provider

GTE-Qwen2-7B-instruct is developed by Alibaba. For the latest information, visit the official documentation.