| sparsity_stage: | |
| sparsity_modifiers: | |
| SparseGPTModifier: {sparsity: 0.5, mask_structure: '2:4'} | |
| run_type: &id001 !!python/object/apply:llmcompressor.recipe.stage.StageRunType [oneshot] | |
| quantization_stage: | |
| quantization_modifiers: | |
| QuantizationModifier: | |
| ignore: [lm_head] | |
| config_groups: | |
| group_0: | |
| weights: {num_bits: 8, type: int, symmetric: true, strategy: channel} | |
| input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true} | |
| targets: [Linear] | |
| run_type: | |