qwen2.5:0.5b-base-q4_K_S

它拥有显著更多的知识，并且在编码和数学方面具有大大增强的能力，这归功于这些领域的专业专家模型。
它在指令遵循、长文本生成（超过 8K 个 token）、理解结构化数据（例如，表格）和生成结构化输出（尤其是在 JSON 格式中）方面表现出显著的进步。它还更能适应各种系统提示，从而改善了聊天机器人的角色扮演和条件设置。
它支持高达 128K 个 token 的长上下文，并且可以生成高达 8K 个 token。
它为超过 29 种语言提供多语言支持，包括中文、英文、法文、西班牙文、葡萄牙文、德文、意大利文、俄文、日文、韩文、越南文、泰文、阿拉伯文等。

请注意：除了 3B 和 72B 型号之外，所有型号均以 Apache 2.0 许可发布，而 3B 和 72B 型号则采用 Qwen 许可。

参考

GitHub

博客文章

HuggingFace

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.

## References

[GitHub](https://github.com/QwenLM/Qwen2.5)

[Blog post](https://qwenlm.github.io/blog/qwen2.5/)

[HuggingFace](https://hugging-face.cn/collections/Qwen/qwen25-66e81a666513e518adb90d9e)

粘贴、拖放或点击以上传图片 (.png, .jpeg, .jpg, .svg, .gif)

Qwen2.5 模型在阿里巴巴最新的大规模数据集上进行了预训练，涵盖高达 18 万亿个 token。 该模型支持高达 128K 个 token 并且支持多语言。

自述文件

参考

Qwen2.5 模型在阿里巴巴最新的大规模数据集上进行了预训练，涵盖高达 18 万亿个 token。该模型支持高达 128K 个 token 并且支持多语言。