add AIBOM

reducto_RolmOCR.json

@@ -0,0 +1,111 @@
+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:d8411c65-830d-47b0-928a-db17d1885512",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:41:39.920661+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "reducto/RolmOCR-9488b32d-f36e-501e-bed2-4e214df3640f",
+            "name": "reducto/RolmOCR",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/reducto/RolmOCR",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "image-text-to-text",
+                    "architectureFamily": "qwen2_5_vl",
+                    "modelArchitecture": "Qwen2_5_VLForConditionalGeneration",
+                    "datasets": [
+                        {
+                            "ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7"
+                        }
+                    ]
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    },
+                    {
+                        "name": "base_model",
+                        "value": "Qwen/Qwen2.5-VL-7B-Instruct"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "reducto"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "Apache-2.0",
+                        "url": "https://spdx.org/licenses/Apache-2.0.html"
+                    }
+                }
+            ],
+            "tags": [
+                "transformers",
+                "safetensors",
+                "qwen2_5_vl",
+                "image-text-to-text",
+                "conversational",
+                "dataset:allenai/olmOCR-mix-0225",
+                "base_model:Qwen/Qwen2.5-VL-7B-Instruct",
+                "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct",
+                "license:apache-2.0",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    },
+    "components": [
+        {
+            "type": "data",
+            "bom-ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7",
+            "name": "allenai/olmOCR-mix-0225",
+            "data": [
+                {
+                    "type": "dataset",
+                    "bom-ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7",
+                    "name": "allenai/olmOCR-mix-0225",
+                    "contents": {
+                        "url": "https://huggingface.co/datasets/allenai/olmOCR-mix-0225",
+                        "properties": [
+                            {
+                                "name": "configs",
+                                "value": "Name of the dataset subset: 00_documents {\"split\": \"train_s2pdf\", \"path\": [\"train-s2pdf.parquet\"]}, {\"split\": \"eval_s2pdf\", \"path\": [\"eval-s2pdf.parquet\"]}"
+                            },
+                            {
+                                "name": "configs",
+                                "value": "Name of the dataset subset: 01_books {\"split\": \"train_iabooks\", \"path\": [\"train-iabooks.parquet\"]}, {\"split\": \"eval_iabooks\", \"path\": [\"eval-iabooks.parquet\"]}"
+                            },
+                            {
+                                "name": "license",
+                                "value": "odc-by"
+                            }
+                        ]
+                    },
+                    "governance": {
+                        "owners": [
+                            {
+                                "organization": {
+                                    "name": "allenai",
+                                    "url": "https://huggingface.co/allenai"
+                                }
+                            }
+                        ]
+                    },
+                    "description": "\n\t\n\t\t\n\t\tolmOCR-mix-0225\n\t\n\nolmOCR-mix-0225 is a dataset of ~250,000 PDF pages which have been OCRed into plain-text in a natural reading order using gpt-4o-2024-08-06 and a special\nprompting strategy that preserves any born-digital content from each page.\nThis dataset can be used to train, fine-tune, or evaluate your own OCR document pipeline.\nQuick links:\n\n\ud83d\udcc3 Paper\n\ud83e\udd17 Model\n\ud83d\udee0\ufe0f Code\n\ud83c\udfae Demo\n\n\n\t\n\t\t\n\t\n\t\n\t\tData Mix\n\t\n\n\n\t\n\t\n\t\n\t\tTable 1: Training set composition by source\n\t\n\n\n\t\n\t\t\nSource\nUnique\u2026 See the full description on the dataset page: https://huggingface.co/datasets/allenai/olmOCR-mix-0225."
+                }
+            ]
+        }
+    ]
+}