ekurtic
/

tmp2

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions

tmp2 / recipe.yaml

ekurtic's picture

Upload folder using huggingface_hub

2130d56 verified about 1 month ago

history blame contribute delete

191 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: ['re:.lm_head', 're:visual.', 're:model.visual.', 're:.mlp.gate$']
	scheme: NVFP4