{"id":957,"slug":"m-a-p--finefineweb-sample","name":"FineFineWeb-sample","author":"m-a-p","description":"\n\t\n\t\t\n\t\tFineFineWeb: A Comprehensive Study on Fine-Grained Domain Web Corpus\n\t\n\narXiv: Coming Soon\nProject Page: Coming Soon\nBlog: Coming Soon\n\n\t\n\t\t\n\t\tData Statistics\n\t\n\n\n\t\n\t\t\nDomain (#tokens/#samples)\nIteration 1 Tokens\nIteration 2 Tokens\nIteration 3 Tokens\nTotal Tokens\nIteration 1 Count\nIteration 2 Count\nIteration 3 Count\nTotal Count\n\n\n\t\t\naerospace\n5.77B\n261.63M\n309.33M\n6.34B\n9100000\n688505\n611034\n10399539\n\n\nagronomy\n13.08B\n947.41M\n229.04M\n14.26B\n15752828\n2711790\n649404\n19114022\n\n\nartistic… See the full description on the dataset page: https://huggingface.co/datasets/m-a-p/FineFineWeb-sample.","tags":"[\"Task_categories:text-Classification\",\"Task_categories:text-Generation\",\"Language:en\",\"Size_categories:100M<n<1B\",\"Format:json\",\"Modality:tabular\"]","license":null,"framework":null,"parameters":null,"downloads":60129,"likes":4,"verified":0,"created_at":"2026-10-04 12:23:25","updated_at":"2026-10-05 08:23:27","source_url":"https://huggingface.co/datasets/m-a-p/FineFineWeb-sample","source_platform":"huggingface","hf_repo_id":"m-a-p/FineFineWeb-sample","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":956,"model_id":957,"version":"v1.0.0","manifest_hash":"ac44b1936ed402ccb398675d6a92f3f84f089a9ae6d7d7c27369603ddd28637e","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/m-a-p--finefineweb-sample/v1.0.0.json","created_at":"2026-10-04 12:23:25"}],"files":[],"signatures":[{"id":1529,"version_id":956,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"c56beed4ef22adc40f8a55f2e7b2bd2bcf0746c401e1657b734451239a4823ce","attestation_type":"registry","signed_at":"2026-10-04 12:23:25"}],"hndl":null}