| { | |
| "api_key": null, | |
| "verify_url": "http://johnrachwan.pythonanywhere.com", | |
| "smash_config": { | |
| "pruners": "None", | |
| "pruning_ratio": 0.0, | |
| "factorizers": "None", | |
| "quantizers": "['awq']", | |
| "weight_quantization_bits": 4, | |
| "output_deviation": 0.005, | |
| "compilers": "None", | |
| "static_batch": true, | |
| "static_shape": true, | |
| "controlnet": "None", | |
| "unet_dim": 4, | |
| "device": "cuda", | |
| "cache_dir": "/ceph/hdd/staff/charpent/.cache/models8b3s1ghc", | |
| "batch_size": 1, | |
| "model_name": "McGill-NLP/Llama-3-8B-Web", | |
| "task": "text_text_generation", | |
| "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_load_fn": "hf-awq" | |
| } | |
| } |