Video-Text-to-Text
Transformers
Safetensors
English
llava_llama
multimodal
video-understanding
region-grounding
3d-reasoning
4d-reasoning
perceptual-distillation
nvila
vila
Instructions to use nvidia/4D-RGPT-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/4D-RGPT-8B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/4D-RGPT-8B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add YAML metadata header to model card
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Model Overview
|
| 2 |
|
| 3 |
### Description:
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: video-text-to-text
|
| 5 |
+
tags:
|
| 6 |
+
- multimodal
|
| 7 |
+
- video-understanding
|
| 8 |
+
- region-grounding
|
| 9 |
+
- 3d-reasoning
|
| 10 |
+
- 4d-reasoning
|
| 11 |
+
- perceptual-distillation
|
| 12 |
+
- nvila
|
| 13 |
+
- vila
|
| 14 |
+
base_model: Efficient-Large-Model/NVILA-Lite-8B
|
| 15 |
+
language:
|
| 16 |
+
- en
|
| 17 |
+
datasets:
|
| 18 |
+
- nvidia/R4D-Bench
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
# Model Overview
|
| 22 |
|
| 23 |
### Description:
|