{
  "@context": "https://schema.org",
  "@id": "https://aggr.aymericbeaumet.com/items/huggingface-co/2026-10-16-scaling-indic-pretraining-2-8-trillion-tokens-and-an-open/#webpage",
  "@type": [
    "WebPage",
    "ArchiveComponent"
  ],
  "articleBody": "",
  "authors": [],
  "captured_at": "2026-10-16T04:55:12.775129010+00:00",
  "category": "ai",
  "content_html": "",
  "content_markdown": "",
  "dateCreated": "2026-10-16T04:55:12.775129010+00:00",
  "date_created": "2026-10-16T01:44:47+00:00",
  "date_modified": "2026-10-16T01:44:47+00:00",
  "date_published": "2026-10-16T01:44:47+00:00",
  "description": "",
  "external_url": "https://huggingface.co/blog/nvidia/scaling-indic-pretraining",
  "git": {
    "commit": "ebb0941c5c06a2ab2377342d607535262a3e969e",
    "path": "items/huggingface-co/2026/10/2026-10-16-scaling-indic-pretraining-2-8-trillion-tokens-and-an-open.md",
    "permalink": "https://github.com/aymericbeaumet/aggr-instance/blob/ebb0941c5c06a2ab2377342d607535262a3e969e/items/huggingface-co/2026/10/2026-10-16-scaling-indic-pretraining-2-8-trillion-tokens-and-an-open.md"
  },
  "id": "urn:aggr:item:c6ee2e51da86ad468c8084078890bc1136d442d4",
  "isBasedOn": {
    "@id": "https://huggingface.co/blog/nvidia/scaling-indic-pretraining"
  },
  "mainEntity": {
    "@id": "https://huggingface.co/blog/nvidia/scaling-indic-pretraining",
    "@type": "CreativeWork",
    "archivedAt": {
      "@id": "https://aggr.aymericbeaumet.com/items/huggingface-co/2026-10-16-scaling-indic-pretraining-2-8-trillion-tokens-and-an-open/#webpage"
    },
    "dateModified": "2026-10-16T01:44:47+00:00",
    "datePublished": "2026-10-16T01:44:47+00:00",
    "headline": "Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline",
    "url": "https://huggingface.co/blog/nvidia/scaling-indic-pretraining"
  },
  "name": "Archived snapshot: Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline",
  "preview": null,
  "reading_minutes": 0,
  "replicated_at": null,
  "source": "huggingface-co",
  "source_name": "Hugging Face - Blog",
  "summary": null,
  "tags": [],
  "temporalCoverage": "2026-10-16T04:55:12.775129010+00:00",
  "title": "Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline",
  "url": "https://aggr.aymericbeaumet.com/items/huggingface-co/2026-10-16-scaling-indic-pretraining-2-8-trillion-tokens-and-an-open/",
  "word_count": 0
}