Subscribe to download
Qwen2.5:1.5b

Qwen2_5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens_ The model supports up to 128K tokens and has multilingual support_

Qwen2_5 is the latest series of Qwen large language models_ For Qwen2_5, a range of base language models and instruction-tuned models are released, with sizes ranging from 0_5 to 72 billion parameters_ Qwen2_5 introduces the following improvements over Qwen2:

It possesses significantly more knowledge and has greatly enhanced capabilities in coding and mathematics, due to specialized expert models in these domains_
It demonstrates significant advancements in instruction following, long-text generation (over 8K tokens), understanding structured data (e_g_, tables), and generating structured outputs, especially in JSON format_ It is also more resilient to diverse system prompts, improving role-play and condition-setting for chatbots_
It supports long contexts of up to 128K tokens and can generate up to 8K tokens_
It offers multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more_

Please 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_