Igeekphone December 27 news, according to OPPO official news, OPPO held a Find X7 series technical communication meeting today, at this meeting, OPPO’s first AI large model – Andean large model AndesGPT was officially released.
According to the official introduction, AndesGPT has a comprehensive and powerful generative vision model, which can accurately understand the semantic understanding of images, and on this basis, realize the recognition and segmentation support for more than 120 types of subjects.
Not only the segmentation accuracy is high to the hair level, but also can support the segmentation and extraction of up to 6 subjects, and can be filled and generated for large area images, and even perfect the generation of natural light and shadow in the picture.
The local image generation time is as low as 6s, which is 60% faster than other models on the same platform, so that the end side can also achieve the generation accuracy and quality comparable to the cloud.
In addition, AndesGPT’s 7 billion parameter language model brings more “intelligence” understanding than the 1 billion parameter large model.
Taking the call summary function as an example, AndesGPT can help users sort through the main points of the call content and accurately output the call summary with the topic, main points and to-do items, which is significantly better than the accuracy of the billion-level end-to-side model.