tolgaakar
/

watt-tool-8B-FP8-Dynamic

compressed-tensors

Model card Files Files and versions Community

watt-tool-8B-FP8-Dynamic / recipe.yaml

tolgaakar's picture

Add model files

4f0c301 13 days ago

history blame contribute delete

136 Bytes

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