File size: 191 Bytes
bda6426 | 1 2 3 4 5 6 7 8 9 | default_stage:
default_modifiers:
SmoothQuantModifier: {smoothing_strength: 0.6}
GPTQModifier:
block_size: 64
scheme: W8A8
targets: Linear
ignore: [lm_head]
|
bda6426 | 1 2 3 4 5 6 7 8 9 | default_stage:
default_modifiers:
SmoothQuantModifier: {smoothing_strength: 0.6}
GPTQModifier:
block_size: 64
scheme: W8A8
targets: Linear
ignore: [lm_head]
|