add AIBOM

neulab_Pangea-7B.json

@@ -0,0 +1,153 @@
+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:2e11cdec-907d-4d94-8fb5-403f936d9153",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:36:57.264117+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "neulab/Pangea-7B-0d33173e-6d50-5129-90ef-bfa7e3206cf4",
+            "name": "neulab/Pangea-7B",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/neulab/Pangea-7B",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "architectureFamily": "qwen2",
+                    "modelArchitecture": "LlavaQwenForCausalLM",
+                    "datasets": [
+                        {
+                            "ref": "neulab/PangeaInstruct-d4b50450-cdc3-5403-9299-37c49a9cf3b7"
+                        }
+                    ]
+                },
+                "properties": [
+                    {
+                        "name": "base_model",
+                        "value": "Qwen/Qwen2-7B-Instruct"
+                    }
+                ],
+                "consideration": {
+                    "useCases": "Pangea-7B follows the architecture of [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT).You could either (1) follow the same model loading procedures as of [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT), an example of loading Pangea-7B directly is shown in the Python code below, or (2) use our hf version of Pangea-7B: [Pangea-7B-hf]https://huggingface.co/neulab/Pangea-7B-hf"
+                }
+            },
+            "authors": [
+                {
+                    "name": "neulab"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "Apache-2.0",
+                        "url": "https://spdx.org/licenses/Apache-2.0.html"
+                    }
+                }
+            ],
+            "description": "- **Model:** Pangea is a fully open-source Multilingual Multimodal Multicultural LLM.- **Date:** Pangea-7B was trained in 2024.- **Training Dataset:** [6M PangeaIns](https://huggingface.co/datasets/neulab/PangeaInstruct).- **Architecture:** Pangea-7B follows the architecture of [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT), with a [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) backbone.",
+            "tags": [
+                "safetensors",
+                "qwen2",
+                "am",
+                "ar",
+                "bg",
+                "bn",
+                "cs",
+                "de",
+                "el",
+                "en",
+                "es",
+                "fa",
+                "fr",
+                "ga",
+                "hi",
+                "id",
+                "ig",
+                "it",
+                "iw",
+                "ja",
+                "jv",
+                "ko",
+                "nl",
+                "mn",
+                "ms",
+                "no",
+                "pl",
+                "pt",
+                "ro",
+                "ru",
+                "si",
+                "su",
+                "sw",
+                "ta",
+                "te",
+                "th",
+                "tr",
+                "uk",
+                "ur",
+                "vi",
+                "zh",
+                "dataset:neulab/PangeaInstruct",
+                "arxiv:2410.16153",
+                "base_model:Qwen/Qwen2-7B-Instruct",
+                "base_model:finetune:Qwen/Qwen2-7B-Instruct",
+                "license:apache-2.0",
+                "region:us"
+            ]
+        }
+    },
+    "components": [
+        {
+            "type": "data",
+            "bom-ref": "neulab/PangeaInstruct-d4b50450-cdc3-5403-9299-37c49a9cf3b7",
+            "name": "neulab/PangeaInstruct",
+            "data": [
+                {
+                    "type": "dataset",
+                    "bom-ref": "neulab/PangeaInstruct-d4b50450-cdc3-5403-9299-37c49a9cf3b7",
+                    "name": "neulab/PangeaInstruct",
+                    "contents": {
+                        "url": "https://huggingface.co/datasets/neulab/PangeaInstruct",
+                        "properties": [
+                            {
+                                "name": "task_categories",
+                                "value": "visual-question-answering, question-answering"
+                            },
+                            {
+                                "name": "language",
+                                "value": "am, ar, bg, bn, cs, de, el, en, es, fa, fr, ga, hi, id, ig, it, iw, ja, jv, ko, nl, mn, ms, no, pl, pt, ro, ru, si, su, sw, ta, te, th, tr, uk, ur, vi, zh"
+                            },
+                            {
+                                "name": "size_categories",
+                                "value": "1M<n<10M"
+                            },
+                            {
+                                "name": "pretty_name",
+                                "value": "PangeaIns"
+                            },
+                            {
+                                "name": "license",
+                                "value": "apache-2.0"
+                            }
+                        ]
+                    },
+                    "governance": {
+                        "owners": [
+                            {
+                                "organization": {
+                                    "name": "neulab",
+                                    "url": "https://huggingface.co/neulab"
+                                }
+                            }
+                        ]
+                    },
+                    "description": "\n\t\n\t\t\n\t\tPangeaInstruct\n\t\n\nPangea: A Fully Open Multilingual Multimodal LLM for 39 Languages\n\ud83c\uddea\ud83c\uddf9 \ud83c\uddf8\ud83c\udde6 \ud83c\udde7\ud83c\uddec \ud83c\udde7\ud83c\udde9 \ud83c\udde8\ud83c\uddff \ud83c\udde9\ud83c\uddea \ud83c\uddec\ud83c\uddf7 \ud83c\uddec\ud83c\udde7 \ud83c\uddfa\ud83c\uddf8 \ud83c\uddea\ud83c\uddf8 \ud83c\uddee\ud83c\uddf7 \ud83c\uddeb\ud83c\uddf7 \ud83c\uddee\ud83c\uddea \ud83c\uddee\ud83c\uddf3 \ud83c\uddee\ud83c\udde9 \ud83c\uddf3\ud83c\uddec \ud83c\uddee\ud83c\uddf9 \ud83c\uddee\ud83c\uddf1 \ud83c\uddef\ud83c\uddf5 \ud83c\uddee\ud83c\udde9 \ud83c\uddf0\ud83c\uddf7 \ud83c\uddf3\ud83c\uddf1 \ud83c\uddf2\ud83c\uddf3 \ud83c\uddf2\ud83c\uddfe \ud83c\uddf3\ud83c\uddf4 \ud83c\uddf5\ud83c\uddf1 \ud83c\uddf5\ud83c\uddf9 \ud83c\udde7\ud83c\uddf7 \ud83c\uddf7\ud83c\uddf4 \ud83c\uddf7\ud83c\uddfa \ud83c\uddf1\ud83c\uddf0 \ud83c\uddee\ud83c\udde9 \ud83c\uddf0\ud83c\uddea \ud83c\uddf9\ud83c\uddff \ud83c\uddf1\ud83c\uddf0 \ud83c\uddee\ud83c\uddf3 \ud83c\uddee\ud83c\uddf3 \ud83c\uddf9\ud83c\udded \ud83c\uddf9\ud83c\uddf7 \ud83c\uddfa\ud83c\udde6 \ud83c\uddf5\ud83c\uddf0 \ud83c\uddee\ud83c\uddf3 \ud83c\uddfb\ud83c\uddf3 \ud83c\udde8\ud83c\uddf3 \ud83c\uddf9\ud83c\uddfc\n\ud83c\udfe0 Homepage | \ud83e\udd16 Pangea-7B | \ud83d\udcca PangeaIns | \ud83e\uddea PangeaBench | \ud83d\udcbb Github | \ud83d\udcc4 Arxiv | \ud83d\udcd5 PDF | \ud83d\udda5\ufe0f Demo\n\n\nThis README provides comprehensive details on the PangeaIns dataset, which\u2026 See the full description on the dataset page: https://huggingface.co/datasets/neulab/PangeaInstruct."
+                }
+            ]
+        }
+    ]
+}