gmonair
/

Qwen2.5-Math-7B-Instruct-W8A16

Model card Files Files and versions Community

File size: 171 Bytes

8d3ca45

DEFAULT_stage:
  DEFAULT_modifiers:
    SmoothQuantModifier: {smoothing_strength: 0.8}
    GPTQModifier:
      targets: Linear
      ignore: [lm_head]
      scheme: W8A16