Instructions to use zeromodels/maxvit_tiny_tf_384_in1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/maxvit_tiny_tf_384_in1k with ZeroModels:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Keras
How to use zeromodels/maxvit_tiny_tf_384_in1k with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://zeromodels/maxvit_tiny_tf_384_in1k") - Notebooks
- Google Colab
- Kaggle
Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)
42d3328 verified | { | |
| "library_name": "zeromodels", | |
| "zeromodels_version": "1.2.1", | |
| "model_module": "zeromodels.models.maxvit", | |
| "model_class": "MaxViTImageClassify", | |
| "variant": "maxvit_tiny_tf_384_in1k", | |
| "weights": "model.weights.h5", | |
| "schema_version": 2, | |
| "weight_dtype": "float32", | |
| "model_type": "maxvit", | |
| "vision_config": { | |
| "stem_width": 64, | |
| "depths": [ | |
| 2, | |
| 2, | |
| 5, | |
| 2 | |
| ], | |
| "embed_dim": [ | |
| 64, | |
| 128, | |
| 256, | |
| 512 | |
| ], | |
| "num_heads": [ | |
| 2, | |
| 4, | |
| 8, | |
| 16 | |
| ], | |
| "window_size": 12, | |
| "image_size": 384, | |
| "num_classes": 1000 | |
| } | |
| } |