alpindale
/

L3.3-70B-Magnum-v4-SE-FP8

compressed-tensors

Model card Files Files and versions Community

L3.3-70B-Magnum-v4-SE-FP8 / recipe.yaml

alpindale's picture

Add files using upload-large-folder tool

3047fa5 verified 8 days ago

history blame contribute delete

136 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: FP8_DYNAMIC