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

NousResearch_Hermes-2-Pro-Llama-3-8B.json

@@ -0,0 +1,121 @@
+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:26a83c5f-701c-441e-8ca4-16e0af2b7494",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:38:54.409420+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "NousResearch/Hermes-2-Pro-Llama-3-8B-fdc16e98-b935-584d-8454-838c6c9395e8",
+            "name": "NousResearch/Hermes-2-Pro-Llama-3-8B",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "text-generation",
+                    "architectureFamily": "llama",
+                    "modelArchitecture": "LlamaForCausalLM",
+                    "datasets": [
+                        {
+                            "ref": "teknium/OpenHermes-2.5-1a7eb3be-7eaa-5577-91f6-d4ad0d639c6c"
+                        }
+                    ]
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    },
+                    {
+                        "name": "base_model",
+                        "value": "NousResearch/Meta-Llama-3-8B"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "NousResearch"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "name": "llama3"
+                    }
+                }
+            ],
+            "description": "Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - `<tools>`, `<tool_call>`, `<tool_response>` and their closing tags are single tokens now.This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AILearn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling",
+            "tags": [
+                "transformers",
+                "safetensors",
+                "llama",
+                "text-generation",
+                "Llama-3",
+                "instruct",
+                "finetune",
+                "chatml",
+                "DPO",
+                "RLHF",
+                "gpt4",
+                "synthetic data",
+                "distillation",
+                "function calling",
+                "json mode",
+                "axolotl",
+                "conversational",
+                "en",
+                "dataset:teknium/OpenHermes-2.5",
+                "base_model:NousResearch/Meta-Llama-3-8B",
+                "base_model:finetune:NousResearch/Meta-Llama-3-8B",
+                "license:llama3",
+                "autotrain_compatible",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    },
+    "components": [
+        {
+            "type": "data",
+            "bom-ref": "teknium/OpenHermes-2.5-1a7eb3be-7eaa-5577-91f6-d4ad0d639c6c",
+            "name": "teknium/OpenHermes-2.5",
+            "data": [
+                {
+                    "type": "dataset",
+                    "bom-ref": "teknium/OpenHermes-2.5-1a7eb3be-7eaa-5577-91f6-d4ad0d639c6c",
+                    "name": "teknium/OpenHermes-2.5",
+                    "contents": {
+                        "url": "https://huggingface.co/datasets/teknium/OpenHermes-2.5",
+                        "properties": [
+                            {
+                                "name": "language",
+                                "value": "eng"
+                            },
+                            {
+                                "name": "pretty_name",
+                                "value": "OpenHermes 2.5"
+                            }
+                        ]
+                    },
+                    "governance": {
+                        "owners": [
+                            {
+                                "organization": {
+                                    "name": "teknium",
+                                    "url": "https://huggingface.co/teknium"
+                                }
+                            }
+                        ]
+                    },
+                    "description": "\n\n\t\n\t\t\n\t\tDataset Card for Dataset Name\n\t\n\nThis is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.\nSupport me on GitHub sponsors <3 : https://github.com/sponsors/teknium1\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\n\t\n\t\t\n\t\tDataset Description\n\t\n\nThe Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.\u2026 See the full description on the dataset page: https://huggingface.co/datasets/teknium/OpenHermes-2.5."
+                }
+            ]
+        }
+    ]
+}