A state-of-the-art multilingual text embedding model from Alibaba's GTE (General Text Embedding) series, built on the Qwen2-1.5B LLM. The model supports up to 8192 tokens and incorporates bidirectional attention mechanisms for enhanced contextual understanding across diverse domains.
gte-Qwen2-1.5B-instruct is the latest model in the GTE (General Text Embedding) model family from Alibaba, built on the Qwen2-1.5B LLM architecture. The model uses the same training data and strategies as the larger gte-Qwen2-7B-instruct model while maintaining a more compact size.
The larger gte-Qwen2-7B-instruct model achieved a score of 70.24 on the MTEB benchmark, outperforming:
The GTE series models are available:
The GTE-Qwen2 series includes:
Developed by Tongyi Lab of Alibaba Group, last updated January 21, 2025. The model represents the state-of-the-art in multilingual embedding models for 2026.
Loading more......