| default_stage: | |
| default_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: [] | |
| QuantizationModifier: | |
| config_groups: | |
| group_0: | |
| targets: [Linear] | |
| weights: | |
| num_bits: 4 | |
| type: float | |
| symmetric: true | |
| group_size: 16 | |
| strategy: tensor_group | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| observer: mse | |
| observer_kwargs: {} | |
| input_activations: | |
| num_bits: 4 | |
| type: float | |
| symmetric: true | |
| group_size: 16 | |
| strategy: tensor_group | |
| block_structure: null | |
| dynamic: local | |
| actorder: null | |
| observer: mse | |
| observer_kwargs: {} | |
| output_activations: null | |
| format: null | |
| targets: [Linear] | |
| ignore: ['re:.*lm_head.*'] | |