Instructions to use BiliSakura/EUPE-ViT-S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BiliSakura/EUPE-ViT-S with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="BiliSakura/EUPE-ViT-S")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BiliSakura/EUPE-ViT-S", dtype="auto") - EUPE
How to use BiliSakura/EUPE-ViT-S with EUPE:
# 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
- Notebooks
- Google Colab
- Kaggle
| { | |
| "depth": 12, | |
| "drop_path_rate": 0.0, | |
| "embed_dim": 384, | |
| "ffn_bias": true, | |
| "ffn_layer": "mlp", | |
| "ffn_ratio": 4.0, | |
| "img_size": 224, | |
| "in_chans": 3, | |
| "layerscale_init": 1e-05, | |
| "mask_k_bias": true, | |
| "model_type": "eupe_vit", | |
| "n_storage_tokens": 4, | |
| "norm_layer": "layernormbf16", | |
| "num_heads": 6, | |
| "patch_size": 16, | |
| "pos_embed_rope_base": 100.0, | |
| "pos_embed_rope_dtype": "fp32", | |
| "pos_embed_rope_jitter_coords": null, | |
| "pos_embed_rope_max_period": null, | |
| "pos_embed_rope_min_period": null, | |
| "pos_embed_rope_normalize_coords": "separate", | |
| "pos_embed_rope_rescale_coords": 2.0, | |
| "pos_embed_rope_shift_coords": null, | |
| "proj_bias": true, | |
| "qkv_bias": true, | |
| "transformers_version": "5.0.0" | |
| } | |