nm-testing
/

granite-8b-code-instruct-128k-W4A16-G128

compressed-tensors

Model card Files Files and versions

granite-8b-code-instruct-128k-W4A16-G128 / recipe.yaml

horheynm's picture

Upload folder using huggingface_hub

a1abb7b verified about 1 year ago

history blame contribute delete

120 Bytes

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