add AIBOM

distilbert_distilbert-base-cased-distilled-squad.json

@@ -0,0 +1,161 @@
+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:2b114990-f3b1-410f-a8d4-d81d465f25d0",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:42:15.918383+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "distilbert/distilbert-base-cased-distilled-squad-1a73168b-1072-535e-9734-342d78002c07",
+            "name": "distilbert/distilbert-base-cased-distilled-squad",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "question-answering",
+                    "architectureFamily": "distilbert",
+                    "modelArchitecture": "DistilBertForQuestionAnswering",
+                    "datasets": [
+                        {
+                            "ref": "squad-bfba1113-705c-51aa-a137-dd682ea9575a"
+                        }
+                    ]
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    }
+                ],
+                "quantitativeAnalysis": {
+                    "performanceMetrics": [
+                        {
+                            "slice": "dataset: squad, split: validation, config: plain_text",
+                            "type": "exact_match",
+                            "value": 79.5998
+                        },
+                        {
+                            "slice": "dataset: squad, split: validation, config: plain_text",
+                            "type": "f1",
+                            "value": 86.9965
+                        }
+                    ]
+                },
+                "consideration": {
+                    "useCases": "This model can be used for question answering."
+                }
+            },
+            "authors": [
+                {
+                    "name": "distilbert"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "Apache-2.0",
+                        "url": "https://spdx.org/licenses/Apache-2.0.html"
+                    }
+                }
+            ],
+            "description": "**Model Description:** The DistilBERT model was proposed in the blog post [Smaller, faster, cheaper, lighter: Introducing DistilBERT, adistilled version of BERT](https://medium.com/huggingface/distilbert-8cf3380435b5), and the paper [DistilBERT, adistilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108). DistilBERT is a small, fast, cheap and light Transformer model trained by distilling BERT base. It has 40% less parameters than *bert-base-uncased*, runs 60% faster while preserving over 95% of BERT's performances as measured on the GLUE language understanding benchmark.This model is a fine-tune checkpoint of [DistilBERT-base-cased](https://huggingface.co/distilbert-base-cased), fine-tuned using (a second step of) knowledge distillation on [SQuAD v1.1](https://huggingface.co/datasets/squad).- **Developed by:** Hugging Face- **Model Type:** Transformer-based language model- **Language(s):** English- **License:** Apache 2.0- **Related Models:** [DistilBERT-base-cased](https://huggingface.co/distilbert-base-cased)- **Resources for more information:**- See [this repository](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) for more about Distil\\* (a class of compressed models including this model)- See [Sanh et al. (2019)](https://arxiv.org/abs/1910.01108) for more information about knowledge distillation and the training procedure",
+            "tags": [
+                "transformers",
+                "pytorch",
+                "tf",
+                "rust",
+                "safetensors",
+                "openvino",
+                "distilbert",
+                "question-answering",
+                "en",
+                "dataset:squad",
+                "arxiv:1910.01108",
+                "arxiv:1910.09700",
+                "license:apache-2.0",
+                "model-index",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    },
+    "components": [
+        {
+            "type": "data",
+            "bom-ref": "squad-bfba1113-705c-51aa-a137-dd682ea9575a",
+            "name": "squad",
+            "data": [
+                {
+                    "type": "dataset",
+                    "bom-ref": "squad-bfba1113-705c-51aa-a137-dd682ea9575a",
+                    "name": "squad",
+                    "contents": {
+                        "url": "https://huggingface.co/datasets/squad",
+                        "properties": [
+                            {
+                                "name": "task_categories",
+                                "value": "question-answering"
+                            },
+                            {
+                                "name": "task_ids",
+                                "value": "extractive-qa"
+                            },
+                            {
+                                "name": "language",
+                                "value": "en"
+                            },
+                            {
+                                "name": "size_categories",
+                                "value": "10K<n<100K"
+                            },
+                            {
+                                "name": "annotations_creators",
+                                "value": "crowdsourced"
+                            },
+                            {
+                                "name": "language_creators",
+                                "value": "crowdsourced, found"
+                            },
+                            {
+                                "name": "pretty_name",
+                                "value": "SQuAD"
+                            },
+                            {
+                                "name": "source_datasets",
+                                "value": "extended|wikipedia"
+                            },
+                            {
+                                "name": "paperswithcode_id",
+                                "value": "squad"
+                            },
+                            {
+                                "name": "configs",
+                                "value": "Name of the dataset subset: plain_text {\"split\": \"train\", \"path\": \"plain_text/train-*\"}, {\"split\": \"validation\", \"path\": \"plain_text/validation-*\"}"
+                            },
+                            {
+                                "name": "license",
+                                "value": "cc-by-sa-4.0"
+                            }
+                        ]
+                    },
+                    "governance": {
+                        "owners": [
+                            {
+                                "organization": {
+                                    "name": "rajpurkar",
+                                    "url": "https://huggingface.co/rajpurkar"
+                                }
+                            }
+                        ]
+                    },
+                    "description": "\n\t\n\t\t\n\t\tDataset Card for SQuAD\n\t\n\n\n\t\n\t\t\n\t\tDataset Summary\n\t\n\nStanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.\nSQuAD 1.1 contains 100,000+ question-answer pairs on 500+ articles.\n\n\t\n\t\t\n\t\tSupported Tasks and Leaderboards\n\t\n\nQuestion Answering.\u2026 See the full description on the dataset page: https://huggingface.co/datasets/rajpurkar/squad."
+                }
+            ]
+        }
+    ]
+}