nm-testing
/

llama2-7b-gsm8k-pt-pruned50-quant-ds

Text Generation

text-generation-inference

Model card Files Files and versions Community

llama2-7b-gsm8k-pt-pruned50-quant-ds / sparse.yaml

mwitiderrick's picture

Create sparse.yaml

bcdea4c verified 8 months ago

history blame contribute delete

No virus

237 Bytes

	test_stage:
	obcq_modifiers:
	SparseGPTModifier:
	sparsity: 0.5
	block_size: 128
	sequential_update: false
	quantize: false
	percdamp: 0.01
	mask_structure: "0:0"
	targets: ["re:model.layers.\\d+$"]