default_stage: default_modifiers: GPTQModifier: config_groups: group_0: targets: ['re:.*mlp\.experts\..*(gate|up|down)_proj$'] weights: num_bits: 4 type: float symmetric: true group_size: 16 strategy: tensor_group dynamic: false actorder: static scale_dtype: torch.float8_e4m3fn observer: nvfp4_expanded_imatrix observer_kwargs: {strict: true} input_activations: {num_bits: 4, type: float, symmetric: true, group_size: 16, strategy: tensor_group, dynamic: local, scale_dtype: torch.float8_e4m3fn, observer: static_minmax} output_activations: null format: null targets: [Linear] ignore: ['re:.*visual.*', lm_head, 're:.*mlp\.gate$', 're:.*self_attn\.indexer\..*'] bypass_divisibility_checks: false requires_calibration_data: true block_size: 128 dampening_frac: 0.01 actorder: static batched_quantization: auto