Instructions to use microsoft/git-large-vqav2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/git-large-vqav2 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="microsoft/git-large-vqav2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("microsoft/git-large-vqav2") model = AutoModelForMultimodalLM.from_pretrained("microsoft/git-large-vqav2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from microsoft/git-large-vqav2: direct link, hf CLI and curl.
- Browser
- Download file 503 Bytes
-
https://huggingface.co/microsoft/git-large-vqav2/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://microsoft/git-large-vqav2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/microsoft/git-large-vqav2/resolve/main/preprocessor_config.json
503 Bytes
| { | |
| "crop_size": { | |
| "height": 420, | |
| "width": 420 | |
| }, | |
| "do_center_crop": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "CLIPImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "processor_class": "GitProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "shortest_edge": 420 | |
| } | |
| } | |