{"id":926,"slug":"ksolovev--fine-news","name":"fine-news","author":"ksolovev","description":"\n\t\n\t\t\n\t\n\t\n\t\tFineNews\n\t\n\nFineNews is a multilingual news-text dataset for language-model research. It filters and deduplicates a 2021–2025 snapshot of the INFINI-NEWS Corpus, which extracts articles from Common Crawl CC-News.\n\n\t\n\t\t\n\t\n\t\n\t\tAt a glance\n\t\n\n\n\t\n\t\t\nMeasure\nFineNews\n\n\n\t\t\nInput articles\n852,824,802 Infini-News rows from 2021–2025\n\n\nOutput\n392,627,654 physical rows\n\n\nFiles\n294,509 Parquet files\n\n\nFolders\n60 publication months (2021-01 to 2025-12), then language\n\n\nLanguage folders\n129… See the full description on the dataset page: https://huggingface.co/datasets/ksolovev/fine-news.","tags":"[\"Task_categories:text-Generation\",\"Size_categories:100M<n<1B\",\"News\",\"Journalism\",\"Media\",\"Common-Crawl\"]","license":null,"framework":null,"parameters":null,"downloads":581470,"likes":30,"verified":0,"created_at":"2026-09-25 14:23:31","updated_at":"2026-09-25 14:23:31","source_url":"https://huggingface.co/datasets/ksolovev/fine-news","source_platform":"huggingface","hf_repo_id":"ksolovev/fine-news","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":925,"model_id":926,"version":"v1.0.0","manifest_hash":"1d7b51d7f32c0681345f028538b4892dce6d2479399b4fbb15e6ea5b81d9a99f","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/ksolovev--fine-news/v1.0.0.json","created_at":"2026-09-25 14:23:31"}],"files":[],"signatures":[{"id":1498,"version_id":925,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"448f5d14cbffa8e53cb74bc4a7a4eba9cd07850eae5889eba7b8fca079d19523","attestation_type":"registry","signed_at":"2026-09-25 14:23:31"}],"hndl":null}