Implemented CR Notes

Signed-off-by: Gal Moyal <[email protected]>

Author: galmo-noma

MLBOM/Dataset/bom.json

@@ -19,6 +19,15 @@
             "publisher": "Hugging Face Inc",
             "name": "wikipedia",
             "version": "b04c8d1ceb2f5cd4588862100d08de323dccfbaa",
+            "data": [
+                {
+                    "type": "dataset",
+                    "name": "wikipedia",
+                    "contents": {
+                        "url": "https://huggingface.co/datasets/wikimedia/wikipedia",
+                    }
+                }
+            ],
             "licenses": [
                 {
                     "license": {
@@ -47,21 +56,63 @@
                     "content": "b04c8d1ceb2f5cd4588862100d08de323dccfbaa"
                 }
             ],
-            "tags": [
-                "task_categories:text-generation",
-                "task_categories:fill-mask",
-                "task_ids:language-modeling",
-                "task_ids:masked-language-modeling",
-                "language:en",
-                "language:es",
-                "size_categories:10M<n<100M",
-                "format:parquet",
-                "modality:text",
-                "library:datasets",
-                "library:dask",
-                "library:mlcroissant",
-                "library:polars",
-                "region:us"
+            "properties": [
+                {
+                    "name": "task_categories",
+                    "value": "text-generation"
+                },
+                {
+                    "name": "task_categories",
+                    "value": "fill-mask"
+                },
+                {
+                    "name": "task_ids",
+                    "value": "language-modeling"
+                },
+                {
+                    "name": "task_ids",
+                    "value": "masked-language-modeling"
+                },
+                {
+                    "name": "language",
+                    "value": "en"
+                },
+                {
+                    "name": "language",
+                    "value": "es"
+                },
+                {
+                    "name": "size_categories",
+                    "value": "10M<n<100M"
+                },
+                {
+                    "name": "format",
+                    "value": "parquet"
+                },
+                {
+                    "name": "modality",
+                    "value": "text"
+                },
+                {
+                    "name": "library",
+                    "value": "datasets"
+                },
+                {
+                    "name": "library",
+                    "value": "dask"
+                },
+                {
+                    "name": "library",
+                    "value": "mlcroissant"
+                },
+                {
+                    "name": "library",
+                    "value": "polars"
+                },
+                {
+                    "name": "region",
+                    "value": "us"
+                }
             ]
         }
     ]

MLBOM/Model/FoundationModels/bom.json

@@ -20,7 +20,28 @@
                 "name": "OpenAI Inc"
             },
             "publisher": "OpenAI Inc",
-            "name": "gpt-4o"
+            "name": "gpt-4o",
+            "modelCard": {
+                "modelParameters": {
+                    "modelArchitecture": "GPT-4",
+                    "inputs": [
+                        {
+                            "format": "string"
+                        },
+                        {
+                            "format": "image"
+                        }
+                    ],
+                    "outputs": [
+                        {
+                            "format": "string"
+                        },
+                        {
+                            "format": "image"
+                        }
+                    ]
+                }
+            }
         }
     ]
 }

MLBOM/Model/OpenSource/bom.json

@@ -40,6 +40,34 @@
                     "content": "cd5ef92a9fb2f889e972770a36d4ed042daf221e"
                 }
             ],
+            "modelCard": {
+                "modelParameters": {
+                    "datasets": [
+                        {
+                            "type": "dataset",
+                            "name": "legacy-datasets/wikipedia",
+                            "contents": {
+                                "url": "https://huggingface.co/datasets/legacy-datasets/wikipedia"
+                            },
+                            "description": "Wikipedia dataset containing cleaned articles of all languages."
+                        },
+                        {
+                            "type": "dataset",
+                            "name": "bookcorpus/bookcorpus",
+                            "contents": {
+                                "url": "https://huggingface.co/datasets/bookcorpus/bookcorpus"
+                            },
+                            "description": "A corpus of fine-grained information and high-level semantics text"
+                        }
+                    ]
+                }
+            },
+            "properties": [
+                {
+                    "name": "region",
+                    "value": "us"
+                }
+            ],
             "tags": [
                 "transformers",
                 "pytorch",
@@ -50,13 +78,9 @@
                 "fill-mask",
                 "exbert",
                 "en",
-                "dataset:bookcorpus",
-                "dataset:wikipedia",
                 "arxiv:1810.04805",
-                "license:apache-2.0",
                 "autotrain_compatible",
-                "endpoints_compatible",
-                "region:us"
+                "endpoints_compatible"
             ]
         }
     ]