rfsousa's picture
Upload folder using huggingface_hub
aec84f0 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.*']
scheme: FP8_BLOCK
bypass_divisibility_checks: false