add AIBOM
#12
by
fatima113
- opened
- reducto_RolmOCR.json +111 -0
reducto_RolmOCR.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bomFormat": "CycloneDX",
|
3 |
+
"specVersion": "1.6",
|
4 |
+
"serialNumber": "urn:uuid:d8411c65-830d-47b0-928a-db17d1885512",
|
5 |
+
"version": 1,
|
6 |
+
"metadata": {
|
7 |
+
"timestamp": "2025-06-05T09:41:39.920661+00:00",
|
8 |
+
"component": {
|
9 |
+
"type": "machine-learning-model",
|
10 |
+
"bom-ref": "reducto/RolmOCR-9488b32d-f36e-501e-bed2-4e214df3640f",
|
11 |
+
"name": "reducto/RolmOCR",
|
12 |
+
"externalReferences": [
|
13 |
+
{
|
14 |
+
"url": "https://huggingface.co/reducto/RolmOCR",
|
15 |
+
"type": "documentation"
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"modelCard": {
|
19 |
+
"modelParameters": {
|
20 |
+
"task": "image-text-to-text",
|
21 |
+
"architectureFamily": "qwen2_5_vl",
|
22 |
+
"modelArchitecture": "Qwen2_5_VLForConditionalGeneration",
|
23 |
+
"datasets": [
|
24 |
+
{
|
25 |
+
"ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7"
|
26 |
+
}
|
27 |
+
]
|
28 |
+
},
|
29 |
+
"properties": [
|
30 |
+
{
|
31 |
+
"name": "library_name",
|
32 |
+
"value": "transformers"
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"name": "base_model",
|
36 |
+
"value": "Qwen/Qwen2.5-VL-7B-Instruct"
|
37 |
+
}
|
38 |
+
]
|
39 |
+
},
|
40 |
+
"authors": [
|
41 |
+
{
|
42 |
+
"name": "reducto"
|
43 |
+
}
|
44 |
+
],
|
45 |
+
"licenses": [
|
46 |
+
{
|
47 |
+
"license": {
|
48 |
+
"id": "Apache-2.0",
|
49 |
+
"url": "https://spdx.org/licenses/Apache-2.0.html"
|
50 |
+
}
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"tags": [
|
54 |
+
"transformers",
|
55 |
+
"safetensors",
|
56 |
+
"qwen2_5_vl",
|
57 |
+
"image-text-to-text",
|
58 |
+
"conversational",
|
59 |
+
"dataset:allenai/olmOCR-mix-0225",
|
60 |
+
"base_model:Qwen/Qwen2.5-VL-7B-Instruct",
|
61 |
+
"base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct",
|
62 |
+
"license:apache-2.0",
|
63 |
+
"text-generation-inference",
|
64 |
+
"endpoints_compatible",
|
65 |
+
"region:us"
|
66 |
+
]
|
67 |
+
}
|
68 |
+
},
|
69 |
+
"components": [
|
70 |
+
{
|
71 |
+
"type": "data",
|
72 |
+
"bom-ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7",
|
73 |
+
"name": "allenai/olmOCR-mix-0225",
|
74 |
+
"data": [
|
75 |
+
{
|
76 |
+
"type": "dataset",
|
77 |
+
"bom-ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7",
|
78 |
+
"name": "allenai/olmOCR-mix-0225",
|
79 |
+
"contents": {
|
80 |
+
"url": "https://huggingface.co/datasets/allenai/olmOCR-mix-0225",
|
81 |
+
"properties": [
|
82 |
+
{
|
83 |
+
"name": "configs",
|
84 |
+
"value": "Name of the dataset subset: 00_documents {\"split\": \"train_s2pdf\", \"path\": [\"train-s2pdf.parquet\"]}, {\"split\": \"eval_s2pdf\", \"path\": [\"eval-s2pdf.parquet\"]}"
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"name": "configs",
|
88 |
+
"value": "Name of the dataset subset: 01_books {\"split\": \"train_iabooks\", \"path\": [\"train-iabooks.parquet\"]}, {\"split\": \"eval_iabooks\", \"path\": [\"eval-iabooks.parquet\"]}"
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"name": "license",
|
92 |
+
"value": "odc-by"
|
93 |
+
}
|
94 |
+
]
|
95 |
+
},
|
96 |
+
"governance": {
|
97 |
+
"owners": [
|
98 |
+
{
|
99 |
+
"organization": {
|
100 |
+
"name": "allenai",
|
101 |
+
"url": "https://huggingface.co/allenai"
|
102 |
+
}
|
103 |
+
}
|
104 |
+
]
|
105 |
+
},
|
106 |
+
"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."
|
107 |
+
}
|
108 |
+
]
|
109 |
+
}
|
110 |
+
]
|
111 |
+
}
|