{"id":891,"slug":"hplt--hplt2.0_cleaned","name":"HPLT2.0_cleaned","author":"HPLT","description":"NB: HPLT2.0 is now superseded by a newer release:\nHPLT3.0\nWe recommed switching to v3.0, unless you have a compelling reason to stay on 2.0.\nThis is a large-scale collection of web-crawled documents in 191 world languages, produced by the HPLT project. \nThe source of the data is mostly Internet Archive with some additions from Common Crawl.\nFor a detailed description of the dataset, please refer to our website and our pre-print.\n\n\t\n\t\t\n\t\n\t\n\t\tThe Cleaned variant of HPLT Datasets v2.0\n\t\n\nThis is… See the full description on the dataset page: https://huggingface.co/datasets/HPLT/HPLT2.0_cleaned.","tags":"[\"Task_categories:fill-Mask\",\"Task_categories:text-Generation\",\"Task_ids:language-Modeling\",\"Multilinguality:multilingual\",\"Language:ace\",\"Language:af\"]","license":null,"framework":null,"parameters":null,"downloads":167335,"likes":45,"verified":0,"created_at":"2026-09-12 11:23:25","updated_at":"2026-09-19 14:23:24","source_url":"https://huggingface.co/datasets/HPLT/HPLT2.0_cleaned","source_platform":"huggingface","hf_repo_id":"HPLT/HPLT2.0_cleaned","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":890,"model_id":891,"version":"v1.0.0","manifest_hash":"ce0abe76610654c2e1c89fd691d2baec753dd6bd50972b9d832c1e3eb889e5ee","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/hplt--hplt2.0_cleaned/v1.0.0.json","created_at":"2026-09-12 11:23:25"}],"files":[],"signatures":[{"id":1463,"version_id":890,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"1bbda21f2ecaaaaf14062e9e9c21f29b583dde8753e622e19947f43dabf7d63a","attestation_type":"registry","signed_at":"2026-09-12 11:23:25"}],"hndl":null}