rdtand's picture
Upload folder using huggingface_hub
1d78f3d verified
default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: ['re:.*lm_head', 're:visual.*', 're:model.visual.*', 're:.*mlp.gate$', 're:.*embed_tokens$',
're:.*shared_expert_gate$', 're:.*linear_attn.conv1d$', 're:.*linear_attn.in_proj_a$',
're:.*linear_attn.in_proj_b$']
scheme: NVFP4
bypass_divisibility_checks: false