nm-testing
/

Llama-3.2-11B-Vision-Instruct-quantized.w8a8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Llama-3.2-11B-Vision-Instruct-quantized.w8a8 / recipe.yaml

shubhrapandit's picture

First model files

0baf979 4 months ago

history blame contribute delete

204 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	dampening_frac: 0.05
	scheme: W8A8
	targets: Linear
	ignore: ['re:.lm_head', 're:multi_modal_projector.', 're:vision_model.*']