cmsptcp
/

Llama-PLLuM-8B-instruct-FP8-Dynamic

compressed-tensors

Model card Files Files and versions

Llama-PLLuM-8B-instruct-FP8-Dynamic / recipe.yaml

cmsptcp's picture

Upload PLLuM-12B-instruct FP8 quantized model

c31f6ce verified 8 months ago

history blame contribute delete

136 Bytes

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