Instructions to use Idan/fga-vqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Idan/fga-vqa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="Idan/fga-vqa")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Idan/fga-vqa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "OpenEndedVQAModel" | |
| ], | |
| "classifier_dropout": 0.3, | |
| "dropout": 0.5, | |
| "dtype": "float32", | |
| "gated_tanh": true, | |
| "hidden_size": 512, | |
| "image_feature_dim": 2048, | |
| "loss_type": "soft_ce", | |
| "mask_padding": true, | |
| "max_question_length": 15, | |
| "model_type": "open_ended_vqa", | |
| "num_answers": 3001, | |
| "num_regions": 36, | |
| "pad_token_id": 0, | |
| "pooling_dim": 16000, | |
| "transformers_version": "5.14.1", | |
| "use_cache": false, | |
| "vocab_size": 8597, | |
| "word_embed_dim": 512 | |
| } | |