shanjiaz
/

nvfp4-quantization-enabled

8-bit precision

compressed-tensors

Model card Files Files and versions

nvfp4-quantization-enabled / recipe.yaml

shanjiaz's picture

Upload folder using huggingface_hub

89612bc verified 12 months ago

History Blame Contribute Delete

130 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: NVFP4