nm-testing
/

Mistral-7B-Instruct-v0.32of4-sparse

compressed-tensors

Model card Files Files and versions Community

Mistral-7B-Instruct-v0.32of4-sparse / recipe.yaml

horheynm's picture

Upload folder using huggingface_hub

c79a836 verified 15 days ago

history blame contribute delete

177 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SparseGPTModifier:
	sparsity: 0.5
	mask_structure: '2:4'
	sequential_update: true
	targets: ['re:model.layers.\d*$']