Instructions to use BiliSakura/AnyUp-transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BiliSakura/AnyUp-transformers with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="BiliSakura/AnyUp-transformers")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BiliSakura/AnyUp-transformers", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download anyup/config.json from BiliSakura/AnyUp-transformers: direct link, hf CLI and curl.
- Browser
- Download file 822 Bytes
-
https://huggingface.co/BiliSakura/AnyUp-transformers/resolve/main/anyup/config.json
- Command line
-
hf download hf://BiliSakura/AnyUp-transformers/anyup/config.json
-
curl -L -o config.json https://huggingface.co/BiliSakura/AnyUp-transformers/resolve/main/anyup/config.json
822 Bytes
| { | |
| "architectures": [ | |
| "AnyUpModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_anyup.AnyUpConfig", | |
| "AutoModel": "modeling_anyup.AnyUpModel" | |
| }, | |
| "custom_pipelines": { | |
| "image-feature-extraction": { | |
| "impl": "pipeline_anyup.AnyUpImageFeatureExtractionPipeline", | |
| "pt": [ | |
| "AutoModel" | |
| ] | |
| } | |
| }, | |
| "dtype": "float32", | |
| "encoder_layers": 2, | |
| "image_size": 224, | |
| "init_gaussian_derivatives": false, | |
| "kernel_size": 1, | |
| "kernel_size_lfu": 5, | |
| "lfu_dim": 128, | |
| "model_type": "anyup", | |
| "num_channels": 3, | |
| "num_heads": 4, | |
| "pad_mode": "reflect", | |
| "q_chunk_size": null, | |
| "qk_dim": 128, | |
| "resblock_kernel_size": 1, | |
| "resblock_num_groups": 8, | |
| "rope_theta": 100, | |
| "transformers_version": "5.15.0", | |
| "use_natten": false, | |
| "variant": "paper", | |
| "window_ratio": 0.1 | |
| } | |