config.json

{"pruner": "None", "pruning_ratio": 0.0, "factorizer": "None", "quantizer": "huggingface-gptq", "n_quantization_bits": 8, "output_deviation": 0.005, "compiler": "None", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": "/ceph/hdd/staff/charpent/.cache/models", "max_batch_size": 1, "image_height": "None", "image_width": "None", "version": "None", "tokenizer_name": "placeholder", "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}