Fidlobabovic/beta-kvantorium-small

RoBerta pretrained on a large corpus of Russion kvantorim data in a self-supervised fashion . This means it was pretrained only on the raw texts only, with no humans labelling them in any way . It can use lots of publicly available data, with an automatic process to generate inputs and labels from those texts . More precisely, it was pre-trained with objective:Automate communication with the Quantorium community and mentors . Automatically automates communication with those who want to use the model to communicate with each other. Automatically generates input and labels based on those texts. Automates the process of generating input and labeling from the raw text. Autom,