Qwen2.5 is the latest generation of the Qwen language models, offering a variety of base and instruction-tuned models with parameter sizes ranging from 0.5 to 72 billion. Key improvements in Qwen2.5 compared to Qwen2 include:
- Enhanced knowledge and significantly improved capabilities in coding and mathematics, thanks to specialized expert models in these areas.
- Advanced performance in instruction following, long-text generation (over 8K tokens), comprehension of structured data (e.g., tables), and structured output generation, particularly in JSON format. It is also more adaptable to varied system prompts, enhancing role-play and condition-setting for chatbots.
- Support for long contexts up to 128K tokens, with the ability to generate 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.
Note: All models except the 3B and 72B are released under the Apache 2.0 license, while the 3B and 72B models are under the Qwen license.
Run Qwen2.5
ollama run qwen2.5