bullerwins
/

gemma-3-27b-it-fp8-Dynamic

Image-Text-to-Text

text-generation-inference

compressed-tensors

Model card Files Files and versions

gemma-3-27b-it-fp8-Dynamic / recipe.yaml

bullerwins's picture

Add files using upload-large-folder tool

6198806 verified about 2 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