File size: 175 Bytes
6914035
 
 
 
 
 
1
2
3
4
5
6
7
default_stage:
  default_modifiers:
    QuantizationModifier:
      targets: [Linear]
      ignore: ['re:.*lm_head.*', 're:.*mlp.gate$', 're:.*self_attn']
      scheme: NVFP4