Add tag, link to paper
Browse filesThis PR ensures people can discover the model more easily
README.md
CHANGED
|
@@ -1,8 +1,11 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
datasets:
|
| 4 |
- liuhaotian/LLaVA-Instruct-150K
|
| 5 |
- OpenGVLab/VideoChat2-IT
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
-
---
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
pipeline_tag: video-text-to-text
|
| 4 |
datasets:
|
| 5 |
- liuhaotian/LLaVA-Instruct-150K
|
| 6 |
- OpenGVLab/VideoChat2-IT
|
| 7 |
language:
|
| 8 |
- en
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
Paper: https://huggingface.co/papers/2409.01071
|