Instructions to use truong-xuan-linh/VQA-vit5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use truong-xuan-linh/VQA-vit5 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("truong-xuan-linh/VQA-vit5") model = AutoModelForSeq2SeqLM.from_pretrained("truong-xuan-linh/VQA-vit5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,4 +16,9 @@ OCR:
|
|
| 16 |
- Post-processing: group layout, divide=4
|
| 17 |
|
| 18 |
Answer:
|
| 19 |
-
- Max length: 56
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
- Post-processing: group layout, divide=4
|
| 17 |
|
| 18 |
Answer:
|
| 19 |
+
- Max length: 56
|
| 20 |
+
|
| 21 |
+
Result:
|
| 22 |
+
- Dev:
|
| 23 |
+
- CIDEr: 3.4616
|
| 24 |
+
- BLEU: 0.4689
|