Connect with us

Hi, what are you looking for?

HEADLINES

Alibaba Cloud launches open-source large vision language model

Qwen-VL is the multimodal version of Qwen-7B, Alibaba Cloud’s 7-billion-parameter model of its large language model Tongyi Qianwen (also available on ModelScope as open-source).

Alibaba Cloud, the digital technology and intelligence backbone of Alibaba Group, launched two open-source large vision language models (LVLM), Qwen-VL and its conversationally fine-tuned Qwen-VL-Chat. The models can comprehend images, texts and bounding boxes in prompts and facilitate multi-round question answering in both English and Chinese.

Qwen-VL is the multimodal version of Qwen-7B, Alibaba Cloud’s 7-billion-parameter model of its large language model Tongyi Qianwen (also available on ModelScope as open-source). Capable of understanding both image inputs and text prompts in English and Chinese, Qwen-VL can perform various tasks such as responding to open-ended queries related to different images and generating image captions.

Qwen-VL-Chat caters to more complex interaction, such as comparing multiple image inputs and engaging in multi-round question answering. Leveraging alignment techniques, this AI assistant exhibits a range of creative capabilities, which include writing poetry and stories based on input images, summarizing the content of multiple pictures, and solving mathematical questions displayed in images.

Contribution to open source and inclusivity

Advertisement. Scroll to continue reading.

In a bid to democratize AI technologies, Alibaba Cloud has shared the model’s code, weights, and documentation with academics, researchers, and commercial institutions worldwide. This contribution to the open-source community is accessible via Alibaba’s AI model community ModelScope and the collaborative AI platform Hugging Face. For commercial uses, companies with over 100 million monthly active users can request a license from Alibaba Cloud.

The introduction of these models, with their ability to extract meaning and information from images, holds the potential to revolutionize the interaction with visual content. For instance, leveraging its image comprehension and question-answering capability, the models could provide information assistance to visually impaired individuals during online shopping in the future.

The Qwen-VL model was pre-trained on image and text datasets. Compared to other open-source large vision language models that can process and understand images in 224*224 resolution, Qwen-VL can handle image input at a resolution of 448*448, resulting in better image recognition and comprehension.

Based on various benchmarks,Qwen-VL recorded outstanding performs on several visual language tasks, including zero-shot captioning, general visual question answering, text-oriented visual question answering, and object detection.

Qwen-VL-Chat has also achieved leading results in both Chinese and English for text-image dialogue and alignment levels with humans, according to the benchmark test of Alibaba Cloud. This test involved over 300 images, 800 questions, and 27 categories.

Advertisement. Scroll to continue reading.

Earlier this month, Alibaba Cloud open sourced its 7-billion-parameter LLMs, Qwen-7B and Qwen-7B-Chat as its ongoing contribution to the open-source community. The two models have had over 400,000 downloads within a month of their launch.

Advertisement
Advertisement
Advertisement

Like Us On Facebook

You May Also Like

HEADLINES

The new investment to build new cloud and AI infrastructure across key international markets also aims to enhance the cloud and AI product suite...

HEADLINES

In a reshaping of its portfolio, ATRAM has rebranded and optimized the newly acquired funds, reflecting a commitment to providing diversified investment options that...

HEADLINES

Under the theme 'Unfolding the Intelligent Future,' ZTE showcased a comprehensive portfolio of ICT products and solutions, featuring 5G wireless, transmission, fixed network, maintenance...

Phones

POCO, a popular technology brand among young tech enthusiasts, is set to redefine the mobile flagship segment with the launch of its new POCO...

MOTORING

One lucky winner will enjoy an all-expenses-paid trip for two to watch Max Verstappen and the Red Bull Racing team at the prestigious Singapore...

HEADLINES

IBM has now open-sourced a family of its most advanced and performant language and code Granite models. By open sourcing these models, IBM is...

HEADLINES

AI is transforming business at an unprecedented pace. Data centers must be designed from the ground up to handle AI’s speed and scale while...

HEADLINES

For the Philippines, PH-CERT and NADPOP estimate that the country needs 180,000 trained and validated cybersecurity professionals to proactively and effectively protect the country’s...

Advertisement