inference-optimization
/

DeepSeek-V3-debug-multiply-FP8_DYNAMIC

compressed-tensors

Model card Files Files and versions

DeepSeek-V3-debug-multiply-FP8_DYNAMIC / recipe.yaml

kylesayrs's picture

Upload folder using huggingface_hub

b702ece verified 4 months ago

history blame contribute delete

136 Bytes

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