Mvp-24
/

Llama-3.2-11b-quantized-model

8-bit precision

compressed-tensors

Model card Files Files and versions

Llama-3.2-11b-quantized-model / recipe.yaml

Mvp-24's picture

Upload 3 files

4450269 verified 6 months ago

177 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	scheme: W8A8
	targets: Linear
	ignore: ['re:.lm_head', 're:multi_modal_projector.', 're:vision_model.*']