| { | |
| "api_key": null, | |
| "verify_url": "http://johnrachwan.pythonanywhere.com", | |
| "smash_config": { | |
| "pruners": "None", | |
| "pruning_ratio": 0.0, | |
| "factorizers": "None", | |
| "quantizers": "['half']", | |
| "n_quantization_bits": 32, | |
| "output_deviation": 0.01, | |
| "compilers": "['x-fast']", | |
| "static_batch": true, | |
| "static_shape": true, | |
| "controlnet": "None", | |
| "unet_dim": 4, | |
| "device": "cuda", | |
| "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsrn4swjrd", | |
| "batch_size": 1, | |
| "model_name": "vit_base_patch16_224.augreg_in21k_ft_in1k", | |
| "max_batch_size": 1, | |
| "qtype_weight": "torch.qint8", | |
| "qtype_activation": "torch.quint8", | |
| "qobserver": "<class 'torch.ao.quantization.observer.MinMaxObserver'>", | |
| "qscheme": "torch.per_tensor_symmetric", | |
| "qconfig": "x86", | |
| "group_size": 128, | |
| "damp_percent": 0.1, | |
| "save_dir": ".models/optimized_model", | |
| "fn_to_compile": "forward", | |
| "save_load_fn": "x-fast" | |
| } | |
| } |