Instructions to use Joe99/visionlanguageTransformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Joe99/visionlanguageTransformer with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="Joe99/visionlanguageTransformer")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, ViltForVisualQuestionAnswering processor = AutoProcessor.from_pretrained("Joe99/visionlanguageTransformer") model = ViltForVisualQuestionAnswering.from_pretrained("Joe99/visionlanguageTransformer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Joe99/visionlanguageTransformer: direct link, hf CLI and curl.
- Browser
- Download file 251 Bytes
-
https://huggingface.co/Joe99/visionlanguageTransformer/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Joe99/visionlanguageTransformer/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Joe99/visionlanguageTransformer/resolve/main/preprocessor_config.json
251 Bytes
| { | |
| "do_normalize": true, | |
| "do_resize": true, | |
| "feature_extractor_type": "ViltFeatureExtractor", | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "resample": 3, | |
| "size": 384, | |
| "size_divisor": 32 | |
| } | |