Instructions to use zeromodels/clip_vit_base_32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/clip_vit_base_32 with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/clip_vit_base_32") - Keras
How to use zeromodels/clip_vit_base_32 with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://zeromodels/clip_vit_base_32") - Notebooks
- Google Colab
- Kaggle
Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)
51e8be5 verified Download zm_preprocessor.json from zeromodels/clip_vit_base_32: direct link, hf CLI and curl.
- Browser
- Download file 508 Bytes
-
https://huggingface.co/zeromodels/clip_vit_base_32/resolve/main/zm_preprocessor.json
- Command line
-
hf download hf://zeromodels/clip_vit_base_32/zm_preprocessor.json
-
curl -L -o zm_preprocessor.json https://huggingface.co/zeromodels/clip_vit_base_32/resolve/main/zm_preprocessor.json
508 Bytes
| { | |
| "library_name": "zeromodels", | |
| "zeromodels_version": "1.1.3", | |
| "preprocessor_module": "zeromodels.models.clip", | |
| "preprocessor_class": "CLIPImageProcessor", | |
| "variant": "clip_vit_base_32", | |
| "image_resolution": 224, | |
| "mean": [ | |
| 0.48145467042922974, | |
| 0.45782750844955444, | |
| 0.40821072459220886 | |
| ], | |
| "std": [ | |
| 0.2686295509338379, | |
| 0.2613025903701782, | |
| 0.27577710151672363 | |
| ], | |
| "do_center_crop": true, | |
| "do_normalize": true, | |
| "do_resize": true, | |
| "data_format": "channels_last" | |
| } |