{"id":40,"slug":"allenai-dolma","name":"Dolma","author":"allenai","description":"Open corpus of 3T tokens for language model pretraining. Sourced from web, academic papers, code, encyclopedic, and book content.","tags":"[\"Dataset\",\"Pretraining\",\"English\",\"3T tokens\"]","license":"ODC-BY","framework":"","parameters":"3T tokens","downloads":4200000,"likes":1800,"verified":1,"created_at":"2026-03-26 03:19:40","updated_at":"2026-03-26 16:38:32","source_url":"https://huggingface.co/datasets/allenai/dolma","source_platform":"huggingface","hf_repo_id":"allenai/dolma","ollama_name":"","category":"dataset","latest_version":"1.0.0","version_count":1,"signature_count":3,"risk_level":"CRITICAL","risk_score":95,"versions":[{"id":40,"model_id":40,"version":"1.0.0","manifest_hash":"F7A49B06E5F024815162","file_count":3,"total_size":50000000000,"r2_manifest_key":null,"created_at":"2026-03-26 03:20:35"}],"files":[{"id":122,"version_id":40,"filename":"data/v1.7/books/train-00000.parquet","sha3_256_hash":"b7b8c1c2c3c4c5c6c7c8d1d2d3d4d5d6d7d8e1e2e3e4e5e6e7e8f1f2f3f4","size":1200000000},{"id":123,"version_id":40,"filename":"data/v1.7/cc/train-00000.parquet","sha3_256_hash":"c7c8d1d2d3d4d5d6d7d8e1e2e3e4e5e6e7e8f1f2f3f4f5f6f7f8a1a2a3a4","size":2400000000},{"id":124,"version_id":40,"filename":"README.md","sha3_256_hash":"d7d8e1e2e3e4e5e6e7e8f1f2f3f4f5f6f7f8a1a2a3a4a5a6a7a8b1b2b3b4","size":32000}],"signatures":[{"id":76,"version_id":40,"signer_did":"did:web:allenai.org:signing","algorithm":"ML-DSA-65","signature_hex":"c177889900112233","attestation_type":"creator","signed_at":"2026-02-20T12:00:00Z"},{"id":77,"version_id":40,"signer_did":"did:web:quantamrkt.com:verification:primary","algorithm":"ML-DSA-87","signature_hex":"d288990011223344","attestation_type":"registry","signed_at":"2026-02-20T12:02:00Z"},{"id":364,"version_id":40,"signer_did":"did:web:quantamrkt.com:chain:authority","algorithm":"ML-DSA-87","signature_hex":"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","attestation_type":"pqc_registry","signed_at":"2026-03-26 16:38:32"}],"hndl":{"id":40,"model_id":40,"risk_level":"CRITICAL","risk_score":95,"shelf_life_years":20,"sensitivity":"restricted","recommendation":"CRITICAL: Training data has 20+ year shelf life. Encrypt with ML-KEM-1024 immediately.","assessed_at":"2026-03-26 03:20:50"}}