Instructions to use bn22/naflexvit_base_patch16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bn22/naflexvit_base_patch16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="bn22/naflexvit_base_patch16")# Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("bn22/naflexvit_base_patch16") model = AutoModel.from_pretrained("bn22/naflexvit_base_patch16") - timm
How to use bn22/naflexvit_base_patch16 with timm:
import timm model = timm.create_model("hf_hub:bn22/naflexvit_base_patch16", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "architecture": "naflexvit_base_patch16_siglip", | |
| "architectures": [ | |
| "TimmWrapperModel" | |
| ], | |
| "do_pooling": true, | |
| "dtype": "float32", | |
| "global_pool": "map", | |
| "initializer_range": 0.02, | |
| "label_names": [], | |
| "model_args": null, | |
| "model_type": "timm_wrapper", | |
| "num_classes": 0, | |
| "num_features": 768, | |
| "pretrained_cfg": { | |
| "classifier": "head", | |
| "crop_mode": "center", | |
| "crop_pct": 1.0, | |
| "custom_load": false, | |
| "first_conv": "embeds.proj", | |
| "fixed_input_size": false, | |
| "input_size": [ | |
| 3, | |
| 384, | |
| 384 | |
| ], | |
| "interpolation": "bicubic", | |
| "license": "apache-2.0", | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "pool_size": null, | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "tag": "v2_webli" | |
| }, | |
| "transformers_version": "5.0.0" | |
| } | |