Learning Fundamental Models with OpenMMLab

1. We will first introduce deep learning foundation model library (MMPreTrain). The milestone works of foundation models will be presented, and we then elaborate the design of our codebase and highlight properties. 2. In this part, we will highlight the newly updated features related to multimodality learning. First, we will discuss the recent progress of the community in multimodal learning, followed by sharing practical examples of how to use MMPreTrain for various multimodal tasks. 3. We then will show how to play foundation models based on image classification and self-supervised leanring. We will illustrate how to use MMPretrain for image classification tasks and self-supervised learning. 4. Finally, we will present how to evaluate the foundation model(LLM, vision model and multi-modality model) with OpenCompass.