WikiText-103: long-context language-modeling benchmark

More than 100 million tokens from Good and Featured Wikipedia articles, kept as whole articles so long-range context is preserved. Comes in a tokenized version and a raw version.

Official page: huggingface.co/datasets/Salesforce/wikitext

SolxLab links to the official source and does not re-host this dataset. Follow the license and terms on the official page.