add AIBOM

Dear model owner(s),
We are a group of researchers investigating the usefulness of sharing AIBOMs (Artificial Intelligence Bill of Materials) to document AI models – AIBOMs are machine-readable structured lists of components (e.g., datasets and models) used to enhance transparency in AI-model supply chains.

To pursue the above-mentioned objective, we identified popular models on HuggingFace and, based on your model card (and some configuration information available in HuggingFace), we generated your AIBOM according to the CyclonDX (v1.6) standard (see https://cyclonedx.org/docs/1.6/json/). AIBOMs are generated as JSON files by using the following open-source supporting tool: https://github.com/MSR4SBOM/ALOHA (technical details are available in the research paper: https://github.com/MSR4SBOM/ALOHA/blob/main/ALOHA.pdf).

The JSON file in this pull request is your AIBOM (see https://github.com/MSR4SBOM/ALOHA/blob/main/documentation.json for details on its structure).

Clearly, the submitted AIBOM matches the current model information, yet it can be easily regenerated when the model evolves, using the aforementioned AIBOM generator tool.

We open this pull request containing an AIBOM of your AI model, and hope it will be considered. We would also like to hear your opinion on the usefulness (or not) of AIBOM by answering a 3-minute anonymous survey: https://forms.gle/WGffSQD5dLoWttEe7.

Thanks in advance, and regards,
Riccardo D’Avino, Fatima Ahmed, Sabato Nocera, Simone Romano, Giuseppe Scanniello (University of Salerno, Italy),
Massimiliano Di Penta (University of Sannio, Italy),
The MSR4SBOM team

arcee-ai_Llama-3.1-SuperNova-Lite.json

@@ -0,0 +1,140 @@
+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:d758fab9-5640-4246-840f-4eb257180280",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:36:31.645371+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "arcee-ai/Llama-3.1-SuperNova-Lite-1c3869d0-46e7-5d1b-ba9c-793f79901c6e",
+            "name": "arcee-ai/Llama-3.1-SuperNova-Lite",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "text-generation",
+                    "architectureFamily": "llama",
+                    "modelArchitecture": "LlamaForCausalLM",
+                    "datasets": [
+                        {
+                            "ref": "arcee-ai/EvolKit-20k-62482fcc-6326-5541-84fe-23ff004cbf51"
+                        }
+                    ]
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    },
+                    {
+                        "name": "base_model",
+                        "value": "meta-llama/Meta-Llama-3.1-8B-Instruct"
+                    }
+                ],
+                "quantitativeAnalysis": {
+                    "performanceMetrics": [
+                        {
+                            "slice": "dataset: HuggingFaceH4/ifeval",
+                            "type": "inst_level_strict_acc and prompt_level_strict_acc",
+                            "value": 80.17
+                        },
+                        {
+                            "slice": "dataset: BBH",
+                            "type": "acc_norm",
+                            "value": 31.57
+                        },
+                        {
+                            "slice": "dataset: hendrycks/competition_math",
+                            "type": "exact_match",
+                            "value": 15.48
+                        },
+                        {
+                            "slice": "dataset: Idavidrein/gpqa",
+                            "type": "acc_norm",
+                            "value": 7.49
+                        },
+                        {
+                            "slice": "dataset: TAUR-Lab/MuSR",
+                            "type": "acc_norm",
+                            "value": 11.67
+                        },
+                        {
+                            "slice": "dataset: TIGER-Lab/MMLU-Pro, split: test, config: main",
+                            "type": "acc",
+                            "value": 31.97
+                        }
+                    ]
+                }
+            },
+            "authors": [
+                {
+                    "name": "arcee-ai"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "name": "llama3"
+                    }
+                }
+            ],
+            "description": "Llama-3.1-SuperNova-Lite is an 8B parameter model developed by Arcee.ai, based on the Llama-3.1-8B-Instruct architecture. It is a distilled version of the larger Llama-3.1-405B-Instruct model, leveraging offline logits extracted from the 405B parameter variant. This 8B variation of Llama-3.1-SuperNova maintains high performance while offering exceptional instruction-following capabilities and domain-specific adaptability.The model was trained using a state-of-the-art distillation pipeline and an instruction dataset generated with [EvolKit](https://github.com/arcee-ai/EvolKit), ensuring accuracy and efficiency across a wide range of tasks. For more information on its training, visit blog.arcee.ai.Llama-3.1-SuperNova-Lite excels in both benchmark performance and real-world applications, providing the power of large-scale models in a more compact, efficient form ideal for organizations seeking high performance with reduced resource requirements.",
+            "tags": [
+                "transformers",
+                "safetensors",
+                "llama",
+                "text-generation",
+                "conversational",
+                "en",
+                "dataset:arcee-ai/EvolKit-20k",
+                "base_model:meta-llama/Llama-3.1-8B-Instruct",
+                "base_model:finetune:meta-llama/Llama-3.1-8B-Instruct",
+                "license:llama3",
+                "model-index",
+                "autotrain_compatible",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    },
+    "components": [
+        {
+            "type": "data",
+            "bom-ref": "arcee-ai/EvolKit-20k-62482fcc-6326-5541-84fe-23ff004cbf51",
+            "name": "arcee-ai/EvolKit-20k",
+            "data": [
+                {
+                    "type": "dataset",
+                    "bom-ref": "arcee-ai/EvolKit-20k-62482fcc-6326-5541-84fe-23ff004cbf51",
+                    "name": "arcee-ai/EvolKit-20k",
+                    "contents": {
+                        "url": "https://huggingface.co/datasets/arcee-ai/EvolKit-20k",
+                        "properties": [
+                            {
+                                "name": "license",
+                                "value": "mit"
+                            }
+                        ]
+                    },
+                    "governance": {
+                        "owners": [
+                            {
+                                "organization": {
+                                    "name": "arcee-ai",
+                                    "url": "https://huggingface.co/arcee-ai"
+                                }
+                            }
+                        ]
+                    },
+                    "description": "\n\t\n\t\t\n\t\tEvolKit-20k\n\t\n\nThis is a subset of a larger dataset generated for the purpose of training our Llama-3.1-SuperNova model. It utilized our EvolKit repository: https://github.com/arcee-ai/EvolKit.\n"
+                }
+            ]
+        }
+    ]
+}