File size: 6,458 Bytes
8e27114 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
{
"bomFormat": "CycloneDX",
"specVersion": "1.6",
"serialNumber": "urn:uuid:ec2a096a-6435-4b15-94a2-3cdfe51237d6",
"version": 1,
"metadata": {
"timestamp": "2025-07-10T08:46:54.205541+00:00",
"component": {
"type": "machine-learning-model",
"bom-ref": "mlabonne/NeuralDaredevil-8B-abliterated-137a94eb-5b88-59d1-88c3-66d6367d780d",
"name": "mlabonne/NeuralDaredevil-8B-abliterated",
"externalReferences": [
{
"url": "https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated",
"type": "documentation"
}
],
"modelCard": {
"modelParameters": {
"task": "text-generation",
"architectureFamily": "llama",
"modelArchitecture": "LlamaForCausalLM",
"datasets": [
{
"ref": "mlabonne/orpo-dpo-mix-40k-898bbffe-f59a-53fe-a5b7-846dc484fbab"
}
]
},
"properties": [
{
"name": "library_name",
"value": "transformers"
}
],
"quantitativeAnalysis": {
"performanceMetrics": [
{
"slice": "dataset: ai2_arc, split: test, config: ARC-Challenge",
"type": "acc_norm",
"value": 69.28
},
{
"slice": "dataset: hellaswag, split: validation",
"type": "acc_norm",
"value": 85.05
},
{
"slice": "dataset: cais/mmlu, split: test, config: all",
"type": "acc",
"value": 69.1
},
{
"slice": "dataset: truthful_qa, split: validation, config: multiple_choice",
"type": "mc2",
"value": 60
},
{
"slice": "dataset: winogrande, split: validation, config: winogrande_xl",
"type": "acc",
"value": 78.69
},
{
"slice": "dataset: gsm8k, split: test, config: main",
"type": "acc",
"value": 71.8
}
]
}
},
"authors": [
{
"name": "mlabonne"
}
],
"licenses": [
{
"license": {
"name": "llama3"
}
}
],
"tags": [
"transformers",
"safetensors",
"llama",
"text-generation",
"dpo",
"conversational",
"dataset:mlabonne/orpo-dpo-mix-40k",
"license:llama3",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
}
},
"components": [
{
"type": "data",
"bom-ref": "mlabonne/orpo-dpo-mix-40k-898bbffe-f59a-53fe-a5b7-846dc484fbab",
"name": "mlabonne/orpo-dpo-mix-40k",
"data": [
{
"type": "dataset",
"bom-ref": "mlabonne/orpo-dpo-mix-40k-898bbffe-f59a-53fe-a5b7-846dc484fbab",
"name": "mlabonne/orpo-dpo-mix-40k",
"contents": {
"url": "https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k",
"properties": [
{
"name": "task_categories",
"value": "text-generation"
},
{
"name": "language",
"value": "en"
},
{
"name": "pretty_name",
"value": "ORPO-DPO-mix-40k"
},
{
"name": "configs",
"value": "Name of the dataset subset: default {\"split\": \"train\", \"path\": \"data/train-*\"}"
},
{
"name": "license",
"value": "apache-2.0"
}
]
},
"governance": {
"owners": [
{
"organization": {
"name": "mlabonne",
"url": "https://huggingface.co/mlabonne"
}
}
]
},
"description": "\n\t\n\t\t\n\t\tORPO-DPO-mix-40k v1.2\n\t\n\n\nThis dataset is designed for ORPO or DPO training.\nSee Fine-tune Llama 3 with ORPO for more information about how to use it.\nIt is a combination of the following high-quality DPO datasets:\n\nargilla/Capybara-Preferences: highly scored chosen answers >=5 (7,424 samples)argilla/distilabel-intel-orca-dpo-pairs: highly scored chosen answers >=9, not in GSM8K (2,299 samples)\nargilla/ultrafeedback-binarized-preferences-cleaned: highly scored chosen answers >=5 (22\u2026 See the full description on the dataset page: https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k."
}
]
}
]
} |