| default_stage: | |
| default_modifiers: | |
| GPTQModifier: | |
| targets: [Linear] | |
| ignore: [lm_head, 're:.*mlp.gate[.].*'] | |
| scheme: W4A16 | |
| bypass_divisibility_checks: false | |
| requires_calibration_data: true | |
| block_size: 128 | |
| dampening_frac: 0.01 | |
| batched_quantization: auto | |
| default_stage: | |
| default_modifiers: | |
| GPTQModifier: | |
| targets: [Linear] | |
| ignore: [lm_head, 're:.*mlp.gate[.].*'] | |
| scheme: W4A16 | |
| bypass_divisibility_checks: false | |
| requires_calibration_data: true | |
| block_size: 128 | |
| dampening_frac: 0.01 | |
| batched_quantization: auto | |