abhishekchohan
/

gemma-3-27b-it-quantized-W4A16

Image-Text-to-Text

text-generation-inference

compressed-tensors

Model card Files Files and versions

gemma-3-27b-it-quantized-W4A16 / recipe.yaml

abhishekchohan's picture

Upload quantized model

348cc75 verified 3 months ago

history blame contribute delete

188 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: ['re:.lm_head', 're:multi_modal_projector.', 're:vision_tower.*']
	targets: [Linear]
	scheme: W4A16