Image Feature Extraction
Transformers
Safetensors
clip_vitb_mini
feature-extraction
clip
knowledge-distillation
consensus-distillation
vit
custom_code
Instructions to use AbstractPhil/clip-vitb-mini-distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AbstractPhil/clip-vitb-mini-distilled with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="AbstractPhil/clip-vitb-mini-distilled", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AbstractPhil/clip-vitb-mini-distilled", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
dist campaign ship: infonce s0 student + standalone loader + full ledgers + frame forensics (loader-fidelity gate PASS zs 0.2668 exact)
dac64fd verified | { | |
| "floor_zs_cifar100": 0.0068, | |
| "teacher_zs_cifar100": 0.7585, | |
| "teacher_zs_cifar10_recheck": 0.946 | |
| } |