noneUsername
/

Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-Token-better

8-bit precision

Model card Files Files and versions Community

Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-Token-better / recipe.yaml

noneUsername's picture

Upload folder using huggingface_hub

f961ed9 verified about 2 months ago

history blame contribute delete

171 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.85}
	GPTQModifier:
	targets: Linear
	ignore: [lm_head]
	scheme: W8A8