Instructions to use johko/mobilesal-multiscale with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use johko/mobilesal-multiscale with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("johko/mobilesal-multiscale", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from johko/mobilesal-multiscale: direct link, hf CLI and curl.
- Browser
- Download file 176 Bytes
-
https://huggingface.co/johko/mobilesal-multiscale/resolve/main/config.json
- Command line
-
hf download hf://johko/mobilesal-multiscale/config.json
-
curl -L -o config.json https://huggingface.co/johko/mobilesal-multiscale/resolve/main/config.json
176 Bytes
| { | |
| "dec_channels": [ | |
| 16, | |
| 24, | |
| 32, | |
| 96, | |
| 320 | |
| ], | |
| "enc_channels": [ | |
| 16, | |
| 24, | |
| 32, | |
| 96, | |
| 320 | |
| ], | |
| "pretrained": true, | |
| "use_carafe": true | |
| } |