recipe.yaml

quant_stage:
  quant_modifiers:
    QuantizationModifier:
      ignore: [lm_head]
      config_groups:
        group_0:
          targets: [Linear]
          weights: {num_bits: 8, type: float, symmetric: true, strategy: tensor, observer: mse}
          input_activations: {num_bits: 8, type: float, symmetric: true, strategy: tensor,
            observer: mse}