| quant_stage: | |
| quant_modifiers: | |
| vLLMQuantizationModifier: | |
| ignore: [lm_head, model.layers.0.mlp.down_proj] | |
| config_groups: | |
| group_0: | |
| weights: {num_bits: 8, type: int, symmetric: true, strategy: tensor} | |
| input_activations: {num_bits: 8, type: int, symmetric: true, strategy: tensor} | |
| targets: [Linear] | |
| SparseGPTModifier: {sparsity: 0.0, quantize: true, sequential_update: false} | |