Files changed (1) hide show
  1. AIDC-AI_Ovis1.6-Gemma2-9B.json +106 -0
AIDC-AI_Ovis1.6-Gemma2-9B.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:7611ea51-f4d2-4d7d-8423-c454737b6e82",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-07-10T09:22:31.938007+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "AIDC-AI/Ovis1.6-Gemma2-9B-e39fac17-8b40-541a-ae36-5ba9dd911393",
11
+ "name": "AIDC-AI/Ovis1.6-Gemma2-9B",
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "task": "image-text-to-text",
21
+ "architectureFamily": "ovis",
22
+ "modelArchitecture": "Ovis",
23
+ "datasets": [
24
+ {
25
+ "ref": "AIDC-AI/Ovis-dataset-2b0700c9-2ab5-5db9-9b2b-d9cfc06e2a69"
26
+ }
27
+ ]
28
+ },
29
+ "properties": [
30
+ {
31
+ "name": "library_name",
32
+ "value": "transformers"
33
+ }
34
+ ]
35
+ },
36
+ "authors": [
37
+ {
38
+ "name": "AIDC-AI"
39
+ }
40
+ ],
41
+ "licenses": [
42
+ {
43
+ "license": {
44
+ "id": "Apache-2.0",
45
+ "url": "https://spdx.org/licenses/Apache-2.0.html"
46
+ }
47
+ }
48
+ ],
49
+ "description": "[GitHub](https://github.com/AIDC-AI/Ovis) | [Demo](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Gemma2-9B) | [Paper](https://arxiv.org/abs/2405.20797)We are excited to announce the open-sourcing of **Ovis-1.6**, our latest multi-modal large language model. Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.<div align=\"center\"><img src=\"https://cdn-uploads.huggingface.co/production/uploads/658a8a837959448ef5500ce5/TIlymOb86R6_Mez3bpmcB.png\" width=\"100%\" /></div>",
50
+ "tags": [
51
+ "transformers",
52
+ "safetensors",
53
+ "ovis",
54
+ "text-generation",
55
+ "MLLM",
56
+ "image-text-to-text",
57
+ "conversational",
58
+ "custom_code",
59
+ "en",
60
+ "dataset:AIDC-AI/Ovis-dataset",
61
+ "arxiv:2405.20797",
62
+ "license:apache-2.0",
63
+ "autotrain_compatible",
64
+ "region:us"
65
+ ]
66
+ }
67
+ },
68
+ "components": [
69
+ {
70
+ "type": "data",
71
+ "bom-ref": "AIDC-AI/Ovis-dataset-2b0700c9-2ab5-5db9-9b2b-d9cfc06e2a69",
72
+ "name": "AIDC-AI/Ovis-dataset",
73
+ "data": [
74
+ {
75
+ "type": "dataset",
76
+ "bom-ref": "AIDC-AI/Ovis-dataset-2b0700c9-2ab5-5db9-9b2b-d9cfc06e2a69",
77
+ "name": "AIDC-AI/Ovis-dataset",
78
+ "contents": {
79
+ "url": "https://huggingface.co/datasets/AIDC-AI/Ovis-dataset",
80
+ "properties": [
81
+ {
82
+ "name": "task_categories",
83
+ "value": "visual-question-answering"
84
+ },
85
+ {
86
+ "name": "license",
87
+ "value": "cc-by-4.0"
88
+ }
89
+ ]
90
+ },
91
+ "governance": {
92
+ "owners": [
93
+ {
94
+ "organization": {
95
+ "name": "AIDC-AI",
96
+ "url": "https://huggingface.co/AIDC-AI"
97
+ }
98
+ }
99
+ ]
100
+ },
101
+ "description": "\n\t\n\t\t\n\t\tUsage\n\t\n\nhttps://github.com/AIDC-AI/Ovis/tree/v1.5?tab=readme-ov-file#dataset\n\n\t\n\t\t\n\t\tDescription\n\t\n\nThis dataset is a collection of multimodal datasets used for training Ovis. Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. For a comprehensive introduction, please refer to the Ovis paper and the Ovis GitHub repo.\n\n\t\n\t\t\n\t\tLicense\n\t\n\nThe files laion-description-11k.json, cc12m-description-1m.json, and\u2026 See the full description on the dataset page: https://huggingface.co/datasets/AIDC-AI/Ovis-dataset."
102
+ }
103
+ ]
104
+ }
105
+ ]
106
+ }