| { | |
| "compression": null, | |
| "dtype": "int4", | |
| "input_info": null, | |
| "optimum_version": "1.24.0.dev0", | |
| "quantization_config": { | |
| "all_layers": null, | |
| "backup_precision": null, | |
| "bits": 4, | |
| "dataset": "contextual", | |
| "gptq": null, | |
| "group_size": 128, | |
| "ignored_scope": null, | |
| "lora_correction": null, | |
| "num_samples": 32, | |
| "processor": null, | |
| "quant_method": "awq", | |
| "ratio": 1.0, | |
| "scale_estimation": null, | |
| "sensitivity_metric": null, | |
| "sym": false, | |
| "tokenizer": null, | |
| "trust_remote_code": true, | |
| "weight_format": "int4" | |
| }, | |
| "save_onnx_model": false, | |
| "transformers_version": "4.46.3" | |
| } | |