Update README.md
Browse files
README.md
CHANGED
@@ -1,30 +1,45 @@
|
|
1 |
-
---
|
2 |
-
license: llama2
|
3 |
-
---
|
4 |
-
|
5 |
-
# v-MLLM Model Card
|
6 |
-
|
7 |
-
## Model details
|
8 |
-
|
9 |
-
**Model type:**
|
10 |
-
v-MLLM is an open-source MLLM trained on Visual-Modality Instruction (VIM) corpus, it can robustly follow the text-modality instructions and visual-modality instructions.
|
11 |
-
|
12 |
-
**Model date:**
|
13 |
-
v-MLLM-7B was trained on January 2024.
|
14 |
-
|
15 |
-
**Github for more information:**
|
16 |
-
https://github.com/VIM-Bench/VIM_TOOL
|
17 |
-
|
18 |
-
## License
|
19 |
-
v-MLLM is licensed under the LLAMA 2 Community License,
|
20 |
-
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
|
21 |
-
|
22 |
-
## Intended use
|
23 |
-
**Primary intended uses:**
|
24 |
-
The primary use of v-MLLM is research on multimodal large language models.
|
25 |
-
|
26 |
-
**Primary intended users:**
|
27 |
-
The primary intended users of the model are researchers in computer vision, natural language processing, machine learning, and artificial intelligence.
|
28 |
-
|
29 |
-
## Training dataset
|
30 |
-
- 846k VIM corpus based on LVIS-Instruct4V corpus.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
---
|
4 |
+
|
5 |
+
# v-MLLM Model Card
|
6 |
+
|
7 |
+
## Model details
|
8 |
+
|
9 |
+
**Model type:**
|
10 |
+
v-MLLM is an open-source MLLM trained on Visual-Modality Instruction (VIM) corpus, it can robustly follow the text-modality instructions and visual-modality instructions.
|
11 |
+
|
12 |
+
**Model date:**
|
13 |
+
v-MLLM-7B was trained on January 2024.
|
14 |
+
|
15 |
+
**Github for more information:**
|
16 |
+
https://github.com/VIM-Bench/VIM_TOOL
|
17 |
+
|
18 |
+
## License
|
19 |
+
v-MLLM is licensed under the LLAMA 2 Community License,
|
20 |
+
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
|
21 |
+
|
22 |
+
## Intended use
|
23 |
+
**Primary intended uses:**
|
24 |
+
The primary use of v-MLLM is research on multimodal large language models.
|
25 |
+
|
26 |
+
**Primary intended users:**
|
27 |
+
The primary intended users of the model are researchers in computer vision, natural language processing, machine learning, and artificial intelligence.
|
28 |
+
|
29 |
+
## Training dataset
|
30 |
+
- 846k VIM corpus based on LVIS-Instruct4V corpus.
|
31 |
+
|
32 |
+
# Citation
|
33 |
+
|
34 |
+
Please kindly cite our paper if you find our resources useful:
|
35 |
+
|
36 |
+
```
|
37 |
+
@misc{lu2023vim,
|
38 |
+
title={VIM: Probing Multimodal Large Language Models for Visual Embedded Instruction Following},
|
39 |
+
author={Yujie Lu and Xiujun Li and William Yang Wang and Yejin Choi},
|
40 |
+
year={2023},
|
41 |
+
eprint={2311.17647},
|
42 |
+
archivePrefix={arXiv},
|
43 |
+
primaryClass={cs.CV}
|
44 |
+
}
|
45 |
+
```
|