Add model card, tags, link to paper
Browse filesThis PR makes sure the model can be viewed from https://huggingface.co/papers/2404.13013, adds a proper model card.
Cheers!
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- FoundationVision/groma_instruct
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: image-text-to-text
|
| 7 |
+
library_name: transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
This repository contains the model of the paper [Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models](https://huggingface.co/papers/2404.13013).
|