darthhexx
/

Meta-Llama-3-8B-Instruct-FP8-Dynamic

Text Generation

compressed-tensors

Model card Files Files and versions Community

Meta-Llama-3-8B-Instruct-FP8-Dynamic / recipe.yaml

darthhexx's picture

Initial commit

ed11463 verified 2 months ago

136 Bytes

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