Qwen-VL

Parameters

9.6B

Published

Aug 24, 2023

Qwen-VL is an AI model developed by Alibaba (China), first published in August 2023. It works in the multimodal, language and vision domain, on tasks such as image captioning, chat, question answering and visual question answering.

Epoch AI has no training-compute estimate for this model. The model has 9,600,000,000 parameters. It was trained on roughly 500B datapoints.

Access: Open weights (restricted use). Its weights are openly available. It is built on top of Qwen-7B. The reference paper has 1,998 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Alibaba
Country of organization: China
Domain: Multimodal, Language, Vision
Task: Image captioning, Chat, Question answering, Visual question answering
Parameters: 9,600,000,000
Dataset size: 500B
Numerical format: BF16
Model accessibility: Open weights (restricted use)
Open weights: Yes
Base model: Qwen-7B
Citations: 1,998
Epoch confidence: Likely