reinforce20001
/

SakuraLLM.Sakura-14B-Qwen2.5-v1.0-W8A8-Int8

Model card Files Files and versions Community

SakuraLLM.Sakura-14B-Qwen2.5-v1.0-W8A8-Int8

File size: 170 Bytes

DEFAULT_stage:
  DEFAULT_modifiers:
    SmoothQuantModifier: {smoothing_strength: 0.8}
    GPTQModifier:
      targets: Linear
      ignore: [lm_head]
      scheme: W8A8