Feature Extraction
Transformers
Safetensors
English
swipe_transformer
multimodal
swipe-keyboard
gesture-recognition
text-prediction
character-prediction
embeddings
custom_code
Instructions to use dleemiller/SwipeALot-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dleemiller/SwipeALot-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="dleemiller/SwipeALot-base", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dleemiller/SwipeALot-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SwipeTransformerModel" | |
| ], | |
| "cls_token_id": 1, | |
| "d_ff": 3072, | |
| "d_model": 768, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 5, | |
| "mask_token_id": 3, | |
| "max_char_len": 48, | |
| "max_path_len": 128, | |
| "model_type": "swipe_transformer", | |
| "n_heads": 12, | |
| "n_layers": 12, | |
| "pad_token_id": 0, | |
| "path_input_dim": 6, | |
| "predict_char": true, | |
| "predict_length": true, | |
| "predict_path": true, | |
| "predict_path_uncertainty": true, | |
| "sep_token_id": 2, | |
| "transformers_version": "4.57.3", | |
| "unk_token_id": 4, | |
| "vocab_size": 43, | |
| "auto_map": { | |
| "AutoConfig": "configuration_swipe.SwipeTransformerConfig", | |
| "AutoModel": "modeling_swipe.SwipeTransformerModel", | |
| "AutoModelForCausalLM": "modeling_swipe.SwipeTransformerModel" | |
| } | |
| } |