Add pipeline tag, transformers library name, and link to Hugging Face paper (#1)
Browse files- Add pipeline tag, transformers library name, and link to Hugging Face paper (553b4fa2ed5cc8dd220e9b5f776f2a2408f98efb)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
@@ -1,5 +1,7 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
3 |
datasets:
|
4 |
- liuhaotian/LLaVA-Pretrain
|
5 |
- lmms-lab/LLaVA-ReCap-558K
|
@@ -10,16 +12,15 @@ datasets:
|
|
10 |
- Zhiqiang007/MathV360K
|
11 |
language:
|
12 |
- en
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
tags:
|
17 |
- LLaVA-OneVision-Manager
|
18 |
- LLaVA-OV-Manager
|
19 |
- Manager
|
20 |
---
|
21 |
|
22 |
-
|
23 |
Model weights for our submission to TCSVT, titled "Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs".
|
24 |
|
25 |
-
Related materials can be found at [Paper](https://
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen2-0.5B-Instruct
|
4 |
+
- google/siglip-so400m-patch14-384
|
5 |
datasets:
|
6 |
- liuhaotian/LLaVA-Pretrain
|
7 |
- lmms-lab/LLaVA-ReCap-558K
|
|
|
12 |
- Zhiqiang007/MathV360K
|
13 |
language:
|
14 |
- en
|
15 |
+
license: mit
|
16 |
+
pipeline_tag: image-text-to-text
|
17 |
+
library_name: transformers
|
18 |
tags:
|
19 |
- LLaVA-OneVision-Manager
|
20 |
- LLaVA-OV-Manager
|
21 |
- Manager
|
22 |
---
|
23 |
|
|
|
24 |
Model weights for our submission to TCSVT, titled "Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs".
|
25 |
|
26 |
+
Related materials can be found at [Paper](https://huggingface.co/papers/2506.11515), [Code](https://github.com/LooperXX/LLaVA-OV-Manager), https://looperxx.github.io/.
|