{"total":8,"page":1,"per_page":20,"results":[{"id":"fineweb-2024","name":"FineWeb 2024","tokens":15000000000000,"license":"odc-by","language":"en","size_gb":44000,"type":"text","updated":"2024-12-01"},{"id":"cc-2024-18","name":"Common Crawl CC-2024-18","tokens":3800000000000,"license":"open","language":"multilingual","size_gb":3400000,"type":"text","updated":"2024-11-15"},{"id":"pile-v2","name":"The Pile v2 Multilingual","tokens":1100000000000,"license":"mit","language":"multilingual","size_gb":1300,"type":"text","updated":"2024-10-20"},{"id":"oasst-rlhf-2","name":"OpenAssistant RLHF v2","tokens":4200000000,"license":"apache-2.0","language":"multilingual","size_gb":4.2,"type":"text","updated":"2024-09-10"},{"id":"laion-5b","name":"LAION-5B Image-Text Pairs","tokens":null,"license":"cc-by-4.0","language":"multilingual","size_gb":240000,"type":"image","pairs":5850000000,"updated":"2024-06-01"},{"id":"dolma-v1.7","name":"Dolma v1.7","tokens":3000000000000,"license":"odbl","language":"en","size_gb":11519,"type":"text","updated":"2024-08-15"},{"id":"redpajama-v2","name":"RedPajama-Data-V2","tokens":30000000000000,"license":"cc-by-4.0","language":"multilingual","size_gb":100000,"type":"text","updated":"2024-07-01"},{"id":"starcoder-data","name":"StarCoder Training Data","tokens":783000000000,"license":"multiple","language":"code-80langs","size_gb":3100,"type":"code","updated":"2024-05-01"}]}