Qwen

Qwen is a series of large language models developed by Alibaba Cloud. The Qwen team is dedicated to pursuing artificial general intelligence, currently focusing on building versatile models, including large language models and large multimodal models. We embrace open-source principles and have previously released the Qwen model series, which includes language models (Qwen), expert models (Qwen-Coder and Qwen-Math), and multimodal models (Qwen-VL and Qwen-Audio). The latest model, Qwen2.5, features: - **Dense, user-friendly, decoder-only language models** available in sizes of 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B, with both base and instruction-tuned variants. - **Pre-trained on our latest large-scale dataset**, containing up to 18 trillion tokens. - **Significant improvements in instruction-following**, long-text generation (over 8K tokens), understanding structured data (e.g., tables), and producing structured outputs, particularly JSON. - **Better adaptability to diverse system prompts**, enhancing role-playing capabilities and conditional settings for chatbots. - **Supports context lengths of up to 128K tokens**, with a generation capacity of up to 8K tokens. - **Multilingual support for over 29 languages**, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.

Qwen is a family of large language models developed by Alibaba Cloud, aiming to pursue general artificial intelligence with a focus on building universal models, including large language models and multimodal models.