| quant_stage: | |
| quant_modifiers: | |
| QuantizationModifier: | |
| ignore: [lm_head] | |
| config_groups: | |
| group_0: | |
| weights: {num_bits: 8, type: int, strategy: channel, dynamic: false, symmetric: true} | |
| input_activations: {num_bits: 8, type: int, strategy: token, dynamic: true, symmetric: true} | |
| targets: [Linear] | |
| pruning_modifiers: | |
| ConstantPruningModifier: | |
| targets: ['re:.*q_proj.weight', 're:.*k_proj.weight', 're:.*v_proj.weight', 're:.*o_proj.weight', | |
| 're:.*gate_proj.weight', 're:.*up_proj.weight', 're:.*down_proj.weight'] | |
| start: 0 | |