Instructions to use Master-AI-Lab/Lumi-Transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Master-AI-Lab/Lumi-Transformer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Master-AI-Lab/Lumi-Transformer") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Master-AI-Lab/Lumi-Transformer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "attention_probs_dropout_prob": 0.0, | |
| "depths": [ | |
| 2, | |
| 2, | |
| 18, | |
| 2 | |
| ], | |
| "drop_path_rate": 0.3, | |
| "embed_dim": 192, | |
| "encoder_stride": 32, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 1536, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-05, | |
| "mlp_ratio": 4.0, | |
| "model_type": "swinv2", | |
| "num_channels": 3, | |
| "num_heads": [ | |
| 6, | |
| 12, | |
| 24, | |
| 48 | |
| ], | |
| "num_layers": 4, | |
| "patch_size": 4, | |
| "pretrained_window_sizes": [ | |
| 0, | |
| 0, | |
| 0, | |
| 0 | |
| ], | |
| "qkv_bias": true, | |
| "transformers_version": "4.28.1", | |
| "use_absolute_embeddings": false, | |
| "window_size": 24 | |
| } | |