File size: 128 Bytes
d51480a |
1 2 3 4 5 6 7 |
DEFAULT_stage:
DEFAULT_modifiers:
QuantizationModifier:
ignore: [lm_head]
targets: [Linear]
scheme: FP8
|
d51480a |
1 2 3 4 5 6 7 |
DEFAULT_stage:
DEFAULT_modifiers:
QuantizationModifier:
ignore: [lm_head]
targets: [Linear]
scheme: FP8
|