RedCaesar
/

Llama-3.2-1B-Instruct-scheme-W8A16

compressed-tensors

Model card Files Files and versions

Llama-3.2-1B-Instruct-scheme-W8A16 / recipe.yaml

RedCaesar's picture

Upload folder using huggingface_hub

d2b63de verified 5 months ago

history blame contribute delete

120 Bytes

	default_stage:
	default_modifiers:
	GPTQModifier:
	scheme: W8A16
	targets: Linear
	ignore: [lm_head]