{
 "name": "Dolma",
 "slug": "dolma",
 "category": "datasets",
 "description": "Allen AI's open pretraining corpus and toolkit.",
 "url": "https://github.com/allenai/dolma",
 "docs_url": "https://allenai.github.io/dolma/",
 "auth": "none",
 "pricing": "free",
 "http_status": null,
 "last_checked_at": "2026-10-14",
 "status": "active",
 "category_name": "Datasets",
 "swarmnest_url": "https://swarmnest.ai/directory/datasets/dolma/"
}