| quant_stage: | |
| quant_modifiers: | |
| GPTQModifier: | |
| config_groups: | |
| group_0: | |
| targets: [Linear] | |
| weights: | |
| num_bits: 4 | |
| type: int | |
| symmetric: true | |
| group_size: 128 | |
| strategy: group | |
| block_structure: null | |
| dynamic: false | |
| actorder: group | |
| scale_dtype: null | |
| zp_dtype: null | |
| observer: memoryless_minmax | |
| observer_kwargs: {} | |
| input_activations: null | |
| output_activations: null | |
| format: null | |
| targets: [Linear] | |
| ignore: [lm_head] | |
| bypass_divisibility_checks: false | |
| block_size: 128 | |
| dampening_frac: 0.01 | |
| actorder: group | |
| offload_hessians: false | |