mkartofel's picture
Add model Qwen3-0.6B-llmcompressor-W8A8-calib-SCiQ
d985b58
raw
history blame contribute delete
170 Bytes
default_stage:
default_modifiers:
SmoothQuantModifier: {smoothing_strength: 0.8}
GPTQModifier:
scheme: W8A8
targets: Linear
ignore: [lm_head]