FYI the roberta-base-uncase does not seem to work:

> OSError: Model name ‘roberta-base-uncase’ was not found in tokenizers model name list (roberta-base, roberta-large, roberta-large-mnli, distilroberta-base, roberta-base-openai-detector, roberta-large-openai-detector). We assumed ‘roberta-base-uncase’ was a path, a model identifier, or url to a directory containing vocabulary files named [‘vocab.json’, ‘merges.txt’] but couldn’t find such vocabulary files at this path or url.