recipe.yaml

quant_stage:
  quant_modifiers:
    QuantizationModifier:
      ignore: ['re:.*lm_head', 're:vision_tower.*', 're:multi_modal_projector.*']
      config_groups:
        group_0:
          weights: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true}
          input_activations: {num_bits: 8, type: float, strategy: tensor, dynamic: false,
            symmetric: true}
          targets: [Linear]
      kv_cache_scheme: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true}