File size: 151 Bytes
4a36662 |
1 2 3 4 5 6 7 |
default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: [lm_head, 're:.*mlp.gate$']
scheme: NVFP4A16
|
4a36662 |
1 2 3 4 5 6 7 |
default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: [lm_head, 're:.*mlp.gate$']
scheme: NVFP4A16
|