Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# TARA Model
|
| 2 |
|
| 3 |
TARA (Time-Aware Retrieval Adaptation) is a multimodal model for video and text understanding.
|
|
@@ -48,7 +65,6 @@ This will download all model weights (may take a few minutes depending on your c
|
|
| 48 |
```
|
| 49 |
|
| 50 |
|
| 51 |
-
|
| 52 |
## Quick Start
|
| 53 |
|
| 54 |
See the script at [demo_usage.py](demo_usage.py) for a quick start. You can run it:
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- sentence-transformers/all-nli
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
base_model:
|
| 10 |
+
- omni-research/Tarsier-7b
|
| 11 |
+
tags:
|
| 12 |
+
- video-retrieval
|
| 13 |
+
- text-to-video-retrieval
|
| 14 |
+
- time-awareness
|
| 15 |
+
- video-models
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
# TARA Model
|
| 19 |
|
| 20 |
TARA (Time-Aware Retrieval Adaptation) is a multimodal model for video and text understanding.
|
|
|
|
| 65 |
```
|
| 66 |
|
| 67 |
|
|
|
|
| 68 |
## Quick Start
|
| 69 |
|
| 70 |
See the script at [demo_usage.py](demo_usage.py) for a quick start. You can run it:
|