sparsity_stage:
  sparsity_modifiers:
    SparseGPTModifier:
      sparsity: 0.5
      mask_structure: '2:4'
      targets: [Linear]
      ignore: ['re:.*lm_head']
quantization_stage:
  quantization_modifiers:
    QuantizationModifier:
      targets: [Linear]
      ignore: [lm_head]
      scheme: FP8_DYNAMIC