qwen

6 种模型尺寸，包括 0.5B、1.8B、4B（默认）、7B、14B、32B（新）和 72B
- ollama run qwen:0.5b
- ollama run qwen:1.8b
- ollama run qwen:4b
- ollama run qwen:7b
- ollama run qwen:14b
- ollama run qwen:32b
- ollama run qwen:72b
- ollama run qwen:110b
在聊天模型的人类偏好方面取得了显著的性能提升
基础模型和聊天模型均支持多语言
稳定支持所有尺寸模型的 32K 上下文长度

原始 Qwen 模型提供四种不同的参数尺寸：1.8B、7B、14B 和 72B。

特性

低成本部署：推断的最低内存需求低于 2GB。
大规模高质量训练语料库：模型在超过 2.2 万亿个词元上进行预训练，包括中文、英文、多语言文本、代码和数学，涵盖通用和专业领域。预训练语料库的分布已通过大量消融实验进行了优化。
良好的性能：Qwen 支持较长的上下文长度（1.8b、7b 和 14b 参数模型为 8K，72b 参数模型为 32K），并且在多个中文和英文下游评估任务（包括常识、推理、代码、数学等）上显著优于同等规模的现有开源模型，甚至在一些基准测试中超过了一些更大规模的模型。
更全面的词汇覆盖范围：与其他基于中文和英文词汇的开源模型相比，Qwen 使用的词汇量超过 150K 个词元。这种词汇对于多种语言更加友好，使用户能够在不扩展词汇量的情况下直接进一步增强某些语言的能力。
系统提示：Qwen 可以通过使用系统提示来实现角色扮演、语言风格转换、任务设置和行为设置。

参考

GitHub

Hugging Face

Qwen 2 is now available [here](https://ollama.org.cn/library/qwen2).

Qwen is a series of transformer-based large language models by Alibaba Cloud, pre-trained on a large volume of data, including web texts, books, code, etc.

### New in Qwen 1.5

- 6 model sizes, including 0.5B, 1.8B, 4B (default), 7B, 14B, 32B (new) and 72B
  * `ollama run qwen:0.5b`
  * `ollama run qwen:1.8b`
  * `ollama run qwen:4b` 
  * `ollama run qwen:7b` 
  * `ollama run qwen:14b`
  * `ollama run qwen:32b`
  * `ollama run qwen:72b`
  * `ollama run qwen:110b`
- Significant performance improvement in human preference for chat models
- Multilingual support of both base and chat models
- Stable support of 32K context length for models of all sizes

The original Qwen model is offered in four different parameter sizes: 1.8B, 7B, 14B, and 72B.

## Features

* **Low-cost deployment**: the minimum memory requirement for inference is less than 2GB.

* **Large-scale high-quality training corpora**: Models are pre-trained on over 2.2 trillion tokens, including Chinese, English, multilingual texts, code, and mathematics, covering general and professional fields. The distribution of the pre-training corpus has been optimized through a large number of ablation experiments.

* **Good performance**: Qwen supports long context lengths (8K on the `1.8b`, `7b` and `14b` parameter models, and 32K on the `72b` parameter model), and significantly surpasses existing open-source models of similar scale on multiple Chinese and English downstream evaluation tasks (including common-sense, reasoning, code, mathematics, etc.), and even surpasses some larger-scale models in several benchmarks.

* **More comprehensive vocabulary coverage**: Compared with other open-source models based on Chinese and English vocabularies, Qwen uses a vocabulary of over 150K tokens. This vocabulary is more friendly to multiple languages, enabling users to directly further enhance the capability for certain languages without expanding the vocabulary.

* **System prompt**: Qwen can realize role playing, language style transfer, task setting, and behavior-setting by using a system prompt.

## Reference

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

[Hugging Face](https://hugging-face.cn/Qwen)

粘贴、拖放或点击上传图像（.png、.jpeg、.jpg、.svg、.gif）