ychen
/

llama-user-sim-70b-fp8

compressed-tensors

Model card Files Files and versions

llama-user-sim-70b-fp8 / recipe.yaml

ychen's picture

Initailize

28219d3 verified 4 months ago

history blame contribute delete

136 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: FP8_DYNAMIC