Image Feature Extraction
Transformers
Safetensors
omni
feature-extraction
histopathology
digital-pathology
foundation-model
vision-transformer
mixture-of-experts
knowledge-distillation
custom_code
Instructions to use sofieneb/omni-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sofieneb/omni-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="sofieneb/omni-tiny", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sofieneb/omni-tiny", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from sofieneb/omni-tiny: direct link, hf CLI and curl.
- Browser
- Download file 683 Bytes
-
https://huggingface.co/sofieneb/omni-tiny/resolve/main/config.json
- Command line
-
hf download hf://sofieneb/omni-tiny/config.json
-
curl -L -o config.json https://huggingface.co/sofieneb/omni-tiny/resolve/main/config.json
683 Bytes
| { | |
| "architectures": [ | |
| "OmniModel" | |
| ], | |
| "model_type": "omni", | |
| "auto_map": { | |
| "AutoConfig": "modeling_omni.OmniConfig", | |
| "AutoModel": "modeling_omni.OmniModel" | |
| }, | |
| "embed_dim": 192, | |
| "depth": 12, | |
| "num_heads": 3, | |
| "mlp_ratio": 3.0, | |
| "num_moe_layers": 3, | |
| "num_experts": 5, | |
| "moe_top_k": 2, | |
| "img_size": 224, | |
| "patch_size": 14, | |
| "teachers": [ | |
| "dinov3vitl16pretrainlvd1689m", | |
| "hoptimus1", | |
| "virchow2", | |
| "uni2h", | |
| "provgigapath", | |
| "kaiko_vitb8", | |
| "titan", | |
| "hiboul", | |
| "h0mini", | |
| "keep" | |
| ], | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "torch_dtype": "float32" | |
| } | |