alpindale
/

Magnum-v2-12B-W8A8-INT8

8-bit precision

compressed-tensors

Model card Files Files and versions

Magnum-v2-12B-W8A8-INT8 / recipe.yaml

alpindale's picture

Add files using upload-large-folder tool

41f9a51 verified 3 months ago

history blame contribute delete

170 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	scheme: W8A8
	targets: Linear
	ignore: [lm_head]