add AIBOM
#10
by
RiccardoDav
- opened
- chandar-lab_NeoBERT.json +115 -0
chandar-lab_NeoBERT.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bomFormat": "CycloneDX",
|
| 3 |
+
"specVersion": "1.6",
|
| 4 |
+
"serialNumber": "urn:uuid:1c879a20-16da-4bf5-901d-c0989128f99f",
|
| 5 |
+
"version": 1,
|
| 6 |
+
"metadata": {
|
| 7 |
+
"timestamp": "2025-06-05T09:41:58.948971+00:00",
|
| 8 |
+
"component": {
|
| 9 |
+
"type": "machine-learning-model",
|
| 10 |
+
"bom-ref": "chandar-lab/NeoBERT-d613029c-4864-500f-a464-bcbfff6cda00",
|
| 11 |
+
"name": "chandar-lab/NeoBERT",
|
| 12 |
+
"externalReferences": [
|
| 13 |
+
{
|
| 14 |
+
"url": "https://huggingface.co/chandar-lab/NeoBERT",
|
| 15 |
+
"type": "documentation"
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"modelCard": {
|
| 19 |
+
"modelParameters": {
|
| 20 |
+
"task": "feature-extraction",
|
| 21 |
+
"architectureFamily": "neobert",
|
| 22 |
+
"modelArchitecture": "NeoBERTLMHead",
|
| 23 |
+
"datasets": [
|
| 24 |
+
{
|
| 25 |
+
"ref": "tiiuae/falcon-refinedweb-0f0f969c-55e1-583f-88a6-b6a6fc0a250c"
|
| 26 |
+
}
|
| 27 |
+
]
|
| 28 |
+
},
|
| 29 |
+
"properties": [
|
| 30 |
+
{
|
| 31 |
+
"name": "library_name",
|
| 32 |
+
"value": "transformers"
|
| 33 |
+
}
|
| 34 |
+
]
|
| 35 |
+
},
|
| 36 |
+
"authors": [
|
| 37 |
+
{
|
| 38 |
+
"name": "chandar-lab"
|
| 39 |
+
}
|
| 40 |
+
],
|
| 41 |
+
"licenses": [
|
| 42 |
+
{
|
| 43 |
+
"license": {
|
| 44 |
+
"id": "MIT",
|
| 45 |
+
"url": "https://spdx.org/licenses/MIT.html"
|
| 46 |
+
}
|
| 47 |
+
}
|
| 48 |
+
],
|
| 49 |
+
"tags": [
|
| 50 |
+
"transformers",
|
| 51 |
+
"safetensors",
|
| 52 |
+
"neobert",
|
| 53 |
+
"fill-mask",
|
| 54 |
+
"feature-extraction",
|
| 55 |
+
"custom_code",
|
| 56 |
+
"en",
|
| 57 |
+
"dataset:tiiuae/falcon-refinedweb",
|
| 58 |
+
"arxiv:2502.19587",
|
| 59 |
+
"license:mit",
|
| 60 |
+
"autotrain_compatible",
|
| 61 |
+
"region:us"
|
| 62 |
+
]
|
| 63 |
+
}
|
| 64 |
+
},
|
| 65 |
+
"components": [
|
| 66 |
+
{
|
| 67 |
+
"type": "data",
|
| 68 |
+
"bom-ref": "tiiuae/falcon-refinedweb-0f0f969c-55e1-583f-88a6-b6a6fc0a250c",
|
| 69 |
+
"name": "tiiuae/falcon-refinedweb",
|
| 70 |
+
"data": [
|
| 71 |
+
{
|
| 72 |
+
"type": "dataset",
|
| 73 |
+
"bom-ref": "tiiuae/falcon-refinedweb-0f0f969c-55e1-583f-88a6-b6a6fc0a250c",
|
| 74 |
+
"name": "tiiuae/falcon-refinedweb",
|
| 75 |
+
"contents": {
|
| 76 |
+
"url": "https://huggingface.co/datasets/tiiuae/falcon-refinedweb",
|
| 77 |
+
"properties": [
|
| 78 |
+
{
|
| 79 |
+
"name": "task_categories",
|
| 80 |
+
"value": "text-generation"
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"name": "language",
|
| 84 |
+
"value": "en"
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"name": "size_categories",
|
| 88 |
+
"value": "100B<n<1T"
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"name": "pretty_name",
|
| 92 |
+
"value": "Falcon RefinedWeb"
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"name": "license",
|
| 96 |
+
"value": "odc-by"
|
| 97 |
+
}
|
| 98 |
+
]
|
| 99 |
+
},
|
| 100 |
+
"governance": {
|
| 101 |
+
"owners": [
|
| 102 |
+
{
|
| 103 |
+
"organization": {
|
| 104 |
+
"name": "tiiuae",
|
| 105 |
+
"url": "https://huggingface.co/tiiuae"
|
| 106 |
+
}
|
| 107 |
+
}
|
| 108 |
+
]
|
| 109 |
+
},
|
| 110 |
+
"description": "\n\t\n\t\t\n\t\t\ud83d\udcc0 Falcon RefinedWeb\n\t\n\nFalcon RefinedWeb is a massive English web dataset built by TII and released under an ODC-By 1.0 license.\nSee the \ud83d\udcd3 paper on arXiv for more details. \nRefinedWeb is built through stringent filtering and large-scale deduplication of CommonCrawl; we found models trained on RefinedWeb to achieve performance in-line or better than models trained on curated datasets, while only relying on web data. \nRefinedWeb is also \"multimodal-friendly\": it contains links and alt\u2026 See the full description on the dataset page: https://huggingface.co/datasets/tiiuae/falcon-refinedweb."
|
| 111 |
+
}
|
| 112 |
+
]
|
| 113 |
+
}
|
| 114 |
+
]
|
| 115 |
+
}
|