Zhipu AI open-source multimodal large model and announced the upcoming release of a new generation of large model products
Recently, Zhipu AI and Tsinghua KEG collaborated to develop and open source a multimodal large model called CogVLM-17B, which can also answer various types of visual problems and achieve deep fusion of visual language features without sacrificing any NLP task performance.The reporter learned that on the multimodal authoritative academic ranking, currently CogVLM-17B is the model with the highest comprehensive performance, achieving SOTA performance on 10 authoritative cross modal benchmarks in 14 datasets, and achieving second place in the remaining 4
Recently, Zhipu AI and Tsinghua KEG collaborated to develop and open source a multimodal large model called CogVLM-17B, which can also answer various types of visual problems and achieve deep fusion of visual language features without sacrificing any NLP task performance.
The reporter learned that on the multimodal authoritative academic ranking, currently CogVLM-17B is the model with the highest comprehensive performance, achieving SOTA performance on 10 authoritative cross modal benchmarks in 14 datasets, and achieving second place in the remaining 4. It is reported that Zhipu AI will also release a new generation of large model products on October 27th. (Dingxi)
Tag: large model of Zhipu AI open-source multimodal and announced
Disclaimer: The content of this article is sourced from the internet. The copyright of the text, images, and other materials belongs to the original author. The platform reprints the materials for the purpose of conveying more information. The content of the article is for reference and learning only, and should not be used for commercial purposes. If it infringes on your legitimate rights and interests, please contact us promptly and we will handle it as soon as possible! We respect copyright and are committed to protecting it. Thank you for sharing.
