{
  "schemaVersion": "1.0",
  "updates": [],
  "companyNews": [],
  "usageGuide": {
    "facts": [
      {
        "key": "limits",
        "label": "Before you start",
        "text": "Code and the reviewed olmOCR-2-7B-1025-FP8 card state Apache 2.0. Local GPU use requires the documented NVIDIA environment and memory; remote inference sends work to the configured server and is not offline.",
        "sourceUrls": [
          "https://github.com/allenai/olmocr/blob/main/README.md",
          "https://github.com/allenai/olmocr/blob/main/LICENSE",
          "https://huggingface.co/allenai/olmOCR-2-7B-1025-FP8"
        ]
      }
    ]
  },
  "id": "b928",
  "language": "en",
  "name": "olmOCR",
  "originalName": "olmOCR",
  "library": "tools",
  "category": "Model development",
  "categoryKey": "模型开发",
  "categoryKeys": [
    "模型开发"
  ],
  "categories": [
    "Model development"
  ],
  "entryPoints": [],
  "summary": "Convert PDFs and document images into reading-order-aware Markdown with a vision-language model.",
  "introduction": "olmOCR linearizes PDFs, PNGs and JPEGs into Markdown for document processing at scale. Its vision-language model handles reading order across columns, tables and equations. Run local GPU inference or connect a remote vLLM server. This is a processing pipeline, not a downloadable corpus; review converted content against the source documents.",
  "capabilities": [],
  "company": {
    "name": "The Allen Institute for Artificial Intelligence",
    "originalName": "The Allen Institute for Artificial Intelligence",
    "country": {
      "codes": [
        "US"
      ],
      "names": [
        "United States"
      ],
      "display": "United States",
      "basis": "company-location",
      "basisLabel": "Published company address"
    }
  },
  "officialUrl": "https://github.com/allenai/olmocr",
  "profileUpdatedOn": "2026-10-23",
  "sources": [
    {
      "kind": "product",
      "url": "https://github.com/allenai/olmocr"
    },
    {
      "kind": "documentation",
      "url": "https://github.com/allenai/olmocr/blob/main/README.md"
    },
    {
      "kind": "documentation",
      "url": "https://huggingface.co/allenai/olmOCR-2-7B-1025-FP8"
    }
  ],
  "news": [],
  "links": {
    "interactive": "products/olmocr--b928.html",
    "reading": "read/en/products/olmocr--b928.html",
    "markdown": "read/en/products/olmocr--b928.md",
    "json": "read/en/products/olmocr--b928.json"
  }
}