File size: 190 Bytes
c5616dd | 1 2 3 4 5 6 7 8 | default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: [lm_head, 're:.*mlp.gate[.].*']
scheme: FP8
bypass_divisibility_checks: false
|
c5616dd | 1 2 3 4 5 6 7 8 | default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: [lm_head, 're:.*mlp.gate[.].*']
scheme: FP8
bypass_divisibility_checks: false
|