Qwen2.5 is part of the Qwen Large Language Model (LLM) series. We released a series of base language models and instruction-tuned language models with parameter scales ranging from 7 billion to 72 billion. Qwen2.5 improves upon Qwen2 in the following ways: * Pre-trained on our latest large-scale dataset containing up to 18 trillion tokens. * Significantly expanded knowledge and greatly enhanced coding and math capabilities due to our domain-expert models. * Major improvements in instruction following, long-text generation (over 8K tokens), structured data understanding (such as tables), and structured output generation (especially JSON). More resilient to diverse system prompts, enhancing chatbot role-playing and conditional setup. * Supports over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic. Usage \| API reference \| Try online ## International If you select the International deployment scope, model inference compute resources are dynamically scheduled worldwide, excluding the Chinese mainland. Static data is stored in your selected region. Supported region: Singapore.