Uploading card files
Browse files
README.md
CHANGED
|
@@ -3,8 +3,35 @@ license: mit
|
|
| 3 |
datasets:
|
| 4 |
- de-Rodrigo/merit
|
| 5 |
language:
|
| 6 |
-
- es
|
| 7 |
- en
|
|
|
|
| 8 |
base_model:
|
| 9 |
- google/paligemma-3b-pt-224
|
| 10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
datasets:
|
| 4 |
- de-Rodrigo/merit
|
| 5 |
language:
|
|
|
|
| 6 |
- en
|
| 7 |
+
- es
|
| 8 |
base_model:
|
| 9 |
- google/paligemma-3b-pt-224
|
| 10 |
+
pipeline_tag: image-text-to-text
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# DONUT Merit
|
| 14 |
+
|
| 15 |
+
<a href="https://x.com/nearcyan/status/1706914605262684394">
|
| 16 |
+
<div style="text-align: center;">
|
| 17 |
+
<picture>
|
| 18 |
+
<source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/de-Rodrigo/donut-merit/resolve/main/assets/dragon_huggingface.png">
|
| 19 |
+
<source media="(prefers-color-scheme: light)" srcset="https://huggingface.co/de-Rodrigo/donut-merit/resolve/main/assets/dragon_huggingface.png">
|
| 20 |
+
<img alt="DragonHuggingFace" src="https://huggingface.co/de-Rodrigo/donut-merit/resolve/main/assets/dragon_huggingface.png" style="width: 200px;">
|
| 21 |
+
</picture>
|
| 22 |
+
</div>
|
| 23 |
+
</a>
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
## Model Architecture
|
| 27 |
+
**This model is based on the Donut architecture and fine-tuned on the Merit dataset for form understanding tasks.**
|
| 28 |
+
|
| 29 |
+
- Backbone: [Paligemma](https://huggingface.co/google/paligemma-3b-pt-224)
|
| 30 |
+
- Training Data: [Merit](https://huggingface.co/datasets/de-Rodrigo/merit)
|
| 31 |
+
|
| 32 |
+
## Example Usage
|
| 33 |
+
|
| 34 |
+
```python
|
| 35 |
+
WIP
|
| 36 |
+
```
|
| 37 |
+
**WIP** 🛠️
|