August 28, 2023: On Friday, Alibaba Reveals the unique AI Models for Picture Display and Difficult Conversations.
The Chinese technology firm stated that its two recent models, Qwen-VL and Qwen-VL-Chat, will be open source meaning that researchers, academics, and leagues worldwide can use them to create their own AI apps without needing to train their systems, saving time and expense.
Alibaba said that Qwen-VL can reply to open-ended queries about different images and generate picture captions.
Qwen-VL-Chat meanwhile caters to more “complex interaction,” according to Alibaba, such as comparing multiple image inputs and answering several rounds of questions. Some tasks that Alibaba says Qwen-VL-Chat can serve include writing stories, creating images based on photos that a user inputs, and solving mathematical equations shown in a picture.
One example Alibaba gave is an input featuring a hospital sign in the Chinese language. The A.I can answer questions about the locations of specific hospital departments by interpreting the character’s image.
So far, much of generative AI, where the technology generates responses based on human inputs, has focused on responding to text. The latest version of OpenAI’s ChatGPT can also understand images and answers in text, much like Qwen-VL-Chat.
Alibaba’s two latest models are built upon the firm’s large language model, Tongyi Qianwen, freed earlier this year. An LLM is an AI model trained on vast amounts of data and underpins chatbot applications.
The Hangzhou-headquartered company this month open-sourced two other AI models. While not making Alibaba any licensing fees, the open-source distribution will help the company get more users for its AI model when its cloud division wants to reignite growth as it prepares to go public.