| quant_stage: | |
| quant_modifiers: | |
| SmoothQuantModifier: | |
| smoothing_strength: 0.8 | |
| mappings: | |
| - !!python/tuple | |
| - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj'] | |
| - re:.*input_layernorm | |
| - !!python/tuple | |
| - ['re:.*gate_proj', 're:.*up_proj'] | |
| - re:.*post_attention_layernorm | |
| ignore: [] | |
| GPTQModifier: | |
| config_groups: | |
| group_0: | |
| targets: [Linear] | |
| weights: | |
| num_bits: 8 | |
| type: int | |
| symmetric: true | |
| group_size: null | |
| strategy: channel | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| scale_dtype: null | |
| zp_dtype: null | |
| observer: minmax | |
| observer_kwargs: {} | |
| input_activations: | |
| num_bits: 8 | |
| type: int | |
| symmetric: true | |
| group_size: null | |
| strategy: tensor | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| scale_dtype: null | |
| zp_dtype: null | |
| observer: minmax | |
| observer_kwargs: {} | |
| output_activations: null | |
| format: null | |
| targets: [Linear] | |
| ignore: [lm_head] | |
| block_size: 128 | |
| dampening_frac: 0.01 | |
| offload_hessians: false | |