qingy2024
/

gemma-3-27b-it-FP8-Dynamic

compressed-tensors

Model card Files Files and versions

gemma-3-27b-it-FP8-Dynamic / recipe.yaml

qingy2024's picture

Duplicate from leon-se/gemma-3-27b-it-FP8-Dynamic

7fb06c0 verified 3 months ago

history blame contribute delete

194 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: ['re:.lm_head', 're:vision_tower.', 're:multi_modal_projector.*']
	targets: [Linear]
	scheme: FP8_DYNAMIC