Muse-12B-NVFP4-4over6 / recipe.yaml
DataSnake's picture
Upload 2 files
ed6b1a9 verified
default_stage:
default_modifiers:
QuantizationModifier:
config_groups:
group_0:
targets: [Linear]
weights:
num_bits: 4
type: float
symmetric: true
group_size: 16
strategy: tensor_group
block_structure: null
dynamic: false
actorder: null
scale_dtype: torch.float8_e4m3fn
zp_dtype: null
observer: memoryless_mse
observer_kwargs: {maxshrink: -1.0, grid: -2.0, norm: 2.0}
input_activations:
num_bits: 4
type: float
symmetric: true
group_size: 16
strategy: tensor_group
block_structure: null
dynamic: local
actorder: null
scale_dtype: torch.float8_e4m3fn
zp_dtype: null
observer: static_minmax
observer_kwargs: {}
output_activations: null
format: null
targets: [Linear]
ignore: [lm_head]