noneUsername
/

L3-8B-Stheno-v3.2-W8A8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

L3-8B-Stheno-v3.2-W8A8 / recipe.yaml

noneUsername's picture

Upload folder using huggingface_hub

a13828d verified about 1 month ago

history blame contribute delete

200 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	sequential_update: true
	targets: Linear
	ignore: [lm_head]
	scheme: W8A8