RedHatAI
/

QwQ-32B-Preview-FP8-dynamic

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

QwQ-32B-Preview-FP8-dynamic / recipe.yaml

Eldar Kurtic

add model

b749fbb over 1 year ago

history blame contribute delete

136 Bytes

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