File size: 287 Bytes
0df6418 | 1 2 3 4 5 6 7 8 9 | default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: [lm_head, 're:.*visual.*', 're:.*linear_attn.in_proj_a$', 're:.*linear_attn.in_proj_b$']
scheme: NVFP4
bypass_divisibility_checks: false
requires_calibration_data: true
|