|
Download README.md from Raasa/moea-compression-checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 668 Bytes
-
https://huggingface.co/Raasa/moea-compression-checkpoints/resolve/main/README.md
- Command line
-
hf download hf://Raasa/moea-compression-checkpoints/README.md
-
curl -L -o README.md https://huggingface.co/Raasa/moea-compression-checkpoints/resolve/main/README.md
668 Bytes
| license: mit | |
| # moea-compression checkpoints | |
| Pretrained ResNet-18 checkpoints for [moea-compression](https://github.com/rkhosrowshahli/moea-compression), | |
| a multi-objective evolutionary search for uniform-binning weight quantization. | |
| | file | dataset | architecture | | |
| |---|---|---| | |
| | `cifar10/resnet18/model_SA_best.pth.tar` | CIFAR-10 | ResNet-18 (3x3 stem, no maxpool) | | |
| | `cifar100/resnet18/model_SA_best.pth.tar` | CIFAR-100 | ResNet-18 (3x3 stem, no maxpool) | | |
| Each file is a `torch.save` dict with keys `state_dict`, `epoch`, `best_sa`. | |
| Loaded automatically by `create_model()` in the moea-compression repo; no | |
| manual download needed. | |