qwen

Qwen 2 is now available here.

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

Hugging Face