qeternity
/

QwQ-32B-Preview-GPTQ-W4A16

compressed-tensors

Model card Files Files and versions Community

QwQ-32B-Preview-GPTQ-W4A16 / recipe.yaml

qeternity's picture

Upload folder using huggingface_hub

f398735 verified about 2 months ago

history blame contribute delete

146 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	targets: Linear
	dampening_frac: 0.1
	ignore: [lm_head]
	scheme: W4A16