Hugging Face's logo

neulab
/
Pangea-7B

Safetensors
qwen2
Model card Files
xet
Community
5

add AIBOM

#5
by sabato-nocera - opened
base: refs/heads/main
←
from: refs/pr/5
Discussion Files changed
+153
-0
Files changed (1) hide show
  1. neulab_Pangea-7B.json +153 -0
neulab_Pangea-7B.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:2e11cdec-907d-4d94-8fb5-403f936d9153",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-06-05T09:36:57.264117+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "neulab/Pangea-7B-0d33173e-6d50-5129-90ef-bfa7e3206cf4",
11
+ "name": "neulab/Pangea-7B",
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/neulab/Pangea-7B",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "architectureFamily": "qwen2",
21
+ "modelArchitecture": "LlavaQwenForCausalLM",
22
+ "datasets": [
23
+ {
24
+ "ref": "neulab/PangeaInstruct-d4b50450-cdc3-5403-9299-37c49a9cf3b7"
25
+ }
26
+ ]
27
+ },
28
+ "properties": [
29
+ {
30
+ "name": "base_model",
31
+ "value": "Qwen/Qwen2-7B-Instruct"
32
+ }
33
+ ],
34
+ "consideration": {
35
+ "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"
36
+ }
37
+ },
38
+ "authors": [
39
+ {
40
+ "name": "neulab"
41
+ }
42
+ ],
43
+ "licenses": [
44
+ {
45
+ "license": {
46
+ "id": "Apache-2.0",
47
+ "url": "https://spdx.org/licenses/Apache-2.0.html"
48
+ }
49
+ }
50
+ ],
51
+ "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.",
52
+ "tags": [
53
+ "safetensors",
54
+ "qwen2",
55
+ "am",
56
+ "ar",
57
+ "bg",
58
+ "bn",
59
+ "cs",
60
+ "de",
61
+ "el",
62
+ "en",
63
+ "es",
64
+ "fa",
65
+ "fr",
66
+ "ga",
67
+ "hi",
68
+ "id",
69
+ "ig",
70
+ "it",
71
+ "iw",
72
+ "ja",
73
+ "jv",
74
+ "ko",
75
+ "nl",
76
+ "mn",
77
+ "ms",
78
+ "no",
79
+ "pl",
80
+ "pt",
81
+ "ro",
82
+ "ru",
83
+ "si",
84
+ "su",
85
+ "sw",
86
+ "ta",
87
+ "te",
88
+ "th",
89
+ "tr",
90
+ "uk",
91
+ "ur",
92
+ "vi",
93
+ "zh",
94
+ "dataset:neulab/PangeaInstruct",
95
+ "arxiv:2410.16153",
96
+ "base_model:Qwen/Qwen2-7B-Instruct",
97
+ "base_model:finetune:Qwen/Qwen2-7B-Instruct",
98
+ "license:apache-2.0",
99
+ "region:us"
100
+ ]
101
+ }
102
+ },
103
+ "components": [
104
+ {
105
+ "type": "data",
106
+ "bom-ref": "neulab/PangeaInstruct-d4b50450-cdc3-5403-9299-37c49a9cf3b7",
107
+ "name": "neulab/PangeaInstruct",
108
+ "data": [
109
+ {
110
+ "type": "dataset",
111
+ "bom-ref": "neulab/PangeaInstruct-d4b50450-cdc3-5403-9299-37c49a9cf3b7",
112
+ "name": "neulab/PangeaInstruct",
113
+ "contents": {
114
+ "url": "https://huggingface.co/datasets/neulab/PangeaInstruct",
115
+ "properties": [
116
+ {
117
+ "name": "task_categories",
118
+ "value": "visual-question-answering, question-answering"
119
+ },
120
+ {
121
+ "name": "language",
122
+ "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"
123
+ },
124
+ {
125
+ "name": "size_categories",
126
+ "value": "1M<n<10M"
127
+ },
128
+ {
129
+ "name": "pretty_name",
130
+ "value": "PangeaIns"
131
+ },
132
+ {
133
+ "name": "license",
134
+ "value": "apache-2.0"
135
+ }
136
+ ]
137
+ },
138
+ "governance": {
139
+ "owners": [
140
+ {
141
+ "organization": {
142
+ "name": "neulab",
143
+ "url": "https://huggingface.co/neulab"
144
+ }
145
+ }
146
+ ]
147
+ },
148
+ "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."
149
+ }
150
+ ]
151
+ }
152
+ ]
153
+ }