Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Paper
•
2506.05176
•
Published
•
78
For further train, this model replace model file with the base model's file. To make sure that model still able to be load with standard sentence-transformers, also change the vocab size in model config. Also, remove template in sentence-transformers config. Do not directly use this model to generate text features!!! Should train on you task first.
Please Check Qwen3-Embedding-0.6B for usage
@article{qwen3embedding,
title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
journal={arXiv preprint arXiv:2506.05176},
year={2025}
}
Base model
Qwen/Qwen3-0.6B-Base