Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ ViLaH (Vision Language Hindi) is a model with 3 billion parameters, fine-tuned f
|
|
| 25 |
* The model's performance may be compromised due to insufficient data and the fact that it was trained for only one epoch.
|
| 26 |
|
| 27 |
# Dataset
|
| 28 |
-
The
|
| 29 |
* [damerajee/clean_hin_vqa](https://huggingface.co/datasets/damerajee/clean_hin_vqa) : This dataset was derived from [Lin-Chen/ShareGPT4V](https://huggingface.co/google/paligemma-3b-pt-224) and filtered to include only images from the COCO dataset. The original dataset was translated and cleaned to ensure high-quality Hindi visual question answering content.
|
| 30 |
|
| 31 |
# How to Use
|
|
|
|
| 25 |
* The model's performance may be compromised due to insufficient data and the fact that it was trained for only one epoch.
|
| 26 |
|
| 27 |
# Dataset
|
| 28 |
+
The model was finetuned on only one dataset
|
| 29 |
* [damerajee/clean_hin_vqa](https://huggingface.co/datasets/damerajee/clean_hin_vqa) : This dataset was derived from [Lin-Chen/ShareGPT4V](https://huggingface.co/google/paligemma-3b-pt-224) and filtered to include only images from the COCO dataset. The original dataset was translated and cleaned to ensure high-quality Hindi visual question answering content.
|
| 30 |
|
| 31 |
# How to Use
|