add AIBOM

google_owlv2-base-patch16-ensemble.json

@@ -0,0 +1,61 @@
+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:e5046994-9a87-48fc-8801-344214a3599a",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:35:20.993969+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "google/owlv2-base-patch16-ensemble-99be0ddf-a3ae-5eb3-a97f-abeb17e238e5",
+            "name": "google/owlv2-base-patch16-ensemble",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/google/owlv2-base-patch16-ensemble",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "zero-shot-object-detection",
+                    "architectureFamily": "owlv2",
+                    "modelArchitecture": "Owlv2ForObjectDetection"
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    }
+                ],
+                "consideration": {
+                    "useCases": "The model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, text-conditioned object detection. We also hope it can be used for interdisciplinary studies of the potential impact of such models, especially in areas that commonly require identifying objects whose label is unavailable during training."
+                }
+            },
+            "authors": [
+                {
+                    "name": "google"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "Apache-2.0",
+                        "url": "https://spdx.org/licenses/Apache-2.0.html"
+                    }
+                }
+            ],
+            "description": "The OWLv2 model (short for Open-World Localization) was proposed in [Scaling Open-Vocabulary Object Detection](https://arxiv.org/abs/2306.09683) by Matthias Minderer, Alexey Gritsenko, Neil Houlsby. OWLv2, like OWL-ViT, is a zero-shot text-conditioned object detection model that can be used to query an image with one or multiple text queries.The model uses CLIP as its multi-modal backbone, with a ViT-like Transformer to get visual features and a causal language model to get the text features. To use CLIP for detection, OWL-ViT removes the final token pooling layer of the vision model and attaches a lightweight classification and box head to each transformer output token. Open-vocabulary classification is enabled by replacing the fixed classification layer weights with the class-name embeddings obtained from the text model. The authors first train CLIP from scratch and fine-tune it end-to-end with the classification and box heads on standard detection datasets using a bipartite matching loss. One or multiple text queries per image can be used to perform zero-shot text-conditioned object detection.",
+            "tags": [
+                "transformers",
+                "pytorch",
+                "safetensors",
+                "owlv2",
+                "zero-shot-object-detection",
+                "vision",
+                "arxiv:2306.09683",
+                "license:apache-2.0",
+                "region:us"
+            ]
+        }
+    }
+}