File size: 146 Bytes
d31fe09 |
1 2 3 4 5 6 7 |
DEFAULT_stage:
DEFAULT_modifiers:
QuantizationModifier:
ignore: [lm_head, 're:.*mlp.gate$']
targets: [Linear]
scheme: FP8
|
d31fe09 |
1 2 3 4 5 6 7 |
DEFAULT_stage:
DEFAULT_modifiers:
QuantizationModifier:
ignore: [lm_head, 're:.*mlp.gate$']
targets: [Linear]
scheme: FP8
|