File size: 213 Bytes
aadbb6b |
1 2 3 4 5 6 7 |
default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: [lm_head, 're:^encoder\.', 're:^adapter\.', 're:^model\.embed_tokens\.', 're:.*layernorm.*']
scheme: NVFP4
|