MPT-7B and The Beginning of Context=Infinity — with Jonathan Frankle and Abhinav Venigalla of MosaicML | Latent Space: The AI Engineer Podcast | Podwise
This podcast episode delves into the work of Mosaic ML, a company specializing in deep learning models, and their experiences in developing sparse models and training large language models. The speakers discuss the technical challenges, creative applications, and ethical considerations surrounding these models and share insights into the training and evaluation processes at Mosaic ML.
