Instructions to use kittn/eupe_vitb16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kittn/eupe_vitb16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="kittn/eupe_vitb16")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("kittn/eupe_vitb16") model = AutoModel.from_pretrained("kittn/eupe_vitb16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Clarify exact parity under bf16 autocast
Verified signaturea46f068 -
Clarify exact RoPE parity patch
Verified signature1add252 -
Clarify fp32-only RoPE parity note
Verified signaturee5c3bbc -
Update README example to 512px
Verified signature78587f1 -
Upload folder using huggingface_hub
Verified signature82d7103 -
initial commit
Verified signature4bc5045