Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

Qwen3 foundation models

Qwen3 foundation models are a family of open-weight large language and multimodal models developed by Alibaba Cloud that serve as versatile base architectures for a broad range of artificial intelligence applications. Pre-trained on extensive multilingual datasets spanning trillions of tokens, these models are designed in multiple parameter scales using both dense and mixture-of-experts architectures. They incorporate hybrid reasoning capabilities that allow dynamic operation between standard direct text generation and extended multi-step reasoning for complex tasks such as coding, mathematics, and logical deduction. In addition to conversational and general generative uses, Qwen3 foundation models serve as foundational backbones and data synthesis engines for specialized downstream adaptations, including text embedding, cross-lingual information retrieval, reranking, autonomous agent workflows, and multimodal understanding across text, vision, and audio.

1 item

Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, Fei Huang, Jingren Zhou

OrganizationsAlibaba GroupTongyi Lab

Why you should read this

Presents the open-source Qwen3 Embedding and reranking model suite across 0.6B to 8B parameters, setting new state-of-the-art performance on multilingual and code retrieval benchmarks through foundation-model-driven synthetic data generation and multi-stage training.

In this work, we introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series, in text embedding and reranking capabilities, built upon the Qwen3 foundation models. Leveraging the Qwen3 LLMs' robust capabilities in multilingual text understanding and generation, our innovative multi-stage training pipeline combines large-scale unsupervised pre-training with supervised fine-tuning on high-quality datasets. Effective model merging strategies further ensure the robustness and adaptability of the Qwen3 Embedding series. During the training process, the Qwen3 LLMs serve not only as backbone models but also play a crucial role in synthesizing high-quality, rich, and diverse training data across multiple domains and languages, thus enhancing the training pipeline. The Qwen3 Embedding series offers a spectrum of model sizes (0.6B, 4B, 8B) for both embedding and reranking tasks, addressing diverse deployment scenarios where users can optimize for either efficiency or effectiveness. Empirical evaluations demonstrate that the Qwen3 Embedding series achieves state-of-the-art results across diverse benchmarks. Notably, it excels on the multilingual evaluation benchmark MTEB for text embedding, as well as in various retrieval tasks, including code retrieval, cross-lingual retrieval and multilingual retrieval. To facilitate reproducibility and promote community-driven research and development, the Qwen3 Embedding models are publicly available under the Apache 2.0 license.

Added

2026-09-25