andecy64
/

Nxcode-CQ-7B-orpo-W8A16

compressed-tensors

Model card Files Files and versions Community

Nxcode-CQ-7B-orpo-W8A16 / recipe.yaml

andecy64

Added model

a4c8ca7 3 months ago

history blame contribute delete

130 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: W8A16