| default_stage: | |
| default_modifiers: | |
| QuantizationModifier: | |
| config_groups: | |
| attention: | |
| targets: ['re:model.*attn.*(wkv|wo_a|wo_b|wq_a|wq_b)$', 're:model.*attn\.compressor.*(wgate|wkv)$'] | |
| weights: | |
| num_bits: 8 | |
| type: float | |
| symmetric: true | |
| group_size: null | |
| strategy: block | |
| block_structure: [128, 128] | |
| dynamic: false | |
| actorder: null | |
| scale_dtype: null | |
| zp_dtype: null | |
| observer: memoryless_minmax | |
| observer_kwargs: {} | |
| input_activations: | |
| num_bits: 8 | |
| type: float | |
| symmetric: true | |
| group_size: 128 | |
| strategy: group | |
| block_structure: null | |
| dynamic: true | |
| actorder: null | |
| scale_dtype: null | |
| zp_dtype: null | |
| observer: null | |
| observer_kwargs: {} | |
| output_activations: null | |
| format: null | |
| experts: | |
| targets: ['re:model.*mlp.*(gate|up|down)_proj$'] | |
| weights: | |
| num_bits: 4 | |
| type: float | |
| symmetric: true | |
| group_size: 16 | |
| strategy: tensor_group | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| scale_dtype: torch.float8_e4m3fn | |
| zp_dtype: null | |
| observer: memoryless_minmax | |
| observer_kwargs: {} | |
| input_activations: | |
| num_bits: 4 | |
| type: float | |
| symmetric: true | |
| group_size: 16 | |
| strategy: tensor_group | |
| block_structure: null | |
| dynamic: local | |
| actorder: null | |
| scale_dtype: torch.float8_e4m3fn | |
| zp_dtype: null | |
| observer: static_minmax | |
| observer_kwargs: {} | |
| output_activations: null | |
| format: null | |
| targets: [Linear] | |
| ignore: [lm_head] | |
| bypass_divisibility_checks: false | |