Qwen/Qwen2.5-72B-Instruct

Qwen2.5-72B-Instruct is a 72.7 billion parameter instruction-tuned causal language model developed by Qwen, built upon the Qwen2 architecture. It features significant improvements in knowledge, coding, and mathematics, alongside enhanced instruction following and long text generation up to 8K tokens. The model supports a 131,072-token context length and offers robust multilingual capabilities across 29 languages, making it suitable for complex, diverse language tasks.