gmonair
/

deepseek-math-7b-rl-W8A16

Model card Files Files and versions Community

File size: 171 Bytes

3c70b2d

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