Instructions to use mb23/FullySpikingAutoEncoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mb23/FullySpikingAutoEncoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="mb23/FullySpikingAutoEncoder", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mb23/FullySpikingAutoEncoder", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "Vth": 0.2, | |
| "a": 0.25, | |
| "aa": 0.5, | |
| "architectures": [ | |
| "FSAEModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_fsae.FSAEConfig", | |
| "AutoModel": "modeling_fsae.FSAEModel" | |
| }, | |
| "dt": 5, | |
| "hidden_dims": [ | |
| 32, | |
| 64, | |
| 128, | |
| 256 | |
| ], | |
| "in_channels": 1, | |
| "k": 20, | |
| "latent_dim": 128, | |
| "model_type": "fsae", | |
| "n_steps": 16, | |
| "scheduled": true, | |
| "tau": 0.25, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.0" | |
| } | |