kaitchup
/

K2-V2-Instruct-nvfp4

8-bit precision

compressed-tensors

Model card Files Files and versions

K2-V2-Instruct-nvfp4 / recipe.yaml

bnjmnmarie's picture

Initial model upload

9d68f65 verified 27 days ago

history blame contribute delete

130 Bytes

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