alpindale
/

Meta-Llama-3.1-8B-Instruct-W8A8-INT8-Dynamic-Per-Token

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Meta-Llama-3.1-8B-Instruct-W8A8-INT8-Dynamic-Per-Token / recipe.yaml

alpindale's picture

Add files using upload-large-folder tool

527114e verified 2 days ago

history blame contribute delete

170 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	targets: Linear
	ignore: [lm_head]
	scheme: W8A8