CalamitousFelicitousness
/

Llama-3.3-70B-Instruct-W8A8-INT8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Llama-3.3-70B-Instruct-W8A8-INT8 / recipe.yaml

CalamitousFelicitousness's picture

CalamitousFelicitousness

Upload folder using huggingface_hub

52fc842 verified 12 days ago

history blame contribute delete

119 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	targets: Linear
	ignore: [lm_head]
	scheme: W8A8