default_stage: | |
default_modifiers: | |
SmoothQuantModifier: {smoothing_strength: 0.5} | |
QuantizationModifier: | |
targets: [Linear] | |
ignore: [lm_head, model.embed_tokens] | |
scheme: W8A8 | |
default_stage: | |
default_modifiers: | |
SmoothQuantModifier: {smoothing_strength: 0.5} | |
QuantizationModifier: | |
targets: [Linear] | |
ignore: [lm_head, model.embed_tokens] | |
scheme: W8A8 | |