LiuRuiLin
Update README.md
ed9b12a verified
metadata
license: unknown
  • Bits: 4
  • Group Size: 128
  • Damp Percent: 0.01
  • Desc Act: false
  • Static Groups: false
  • Sym: false
  • True Sequential: false
  • LM Head: true
  • Model Name or Path: null
  • Model File Base Name: model
  • Quant Method: gptq
  • Checkpoint Format: gptq
  • Meta:
    • Quantizer: intel/auto-round:0.1
    • Packer: autogptq:0.8.0.dev1
    • Iters: 400
    • LR: 0.0025
    • MinMax LR: 0.0025
    • Enable MinMax Tuning: true
    • Use Quant Input: false
    • Scale Dtype: torch.float16