| quant_stage: | |
| quant_modifiers: | |
| QuantizationModifier: | |
| config_groups: | |
| group_0: | |
| targets: [Linear] | |
| weights: | |
| num_bits: 8 | |
| type: float | |
| symmetric: true | |
| group_size: null | |
| strategy: tensor | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| observer: minmax | |
| observer_kwargs: {} | |
| is_mx: false | |
| input_activations: | |
| num_bits: 8 | |
| type: float | |
| symmetric: true | |
| group_size: null | |
| strategy: tensor | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| observer: minmax | |
| observer_kwargs: {} | |
| is_mx: false | |
| output_activations: null | |
| targets: [Linear] | |
| ignore: [lm_head] | |
| kv_cache_scheme: | |
| num_bits: 8 | |
| type: float | |
| symmetric: true | |
| group_size: null | |
| strategy: tensor | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| observer: minmax | |
| observer_kwargs: {} | |
| is_mx: false | |