nm-testing
/

Qwen2-VL-2B-Instruct-Sparse-0.6

compressed-tensors

Model card Files Files and versions Community

Qwen2-VL-2B-Instruct-Sparse-0.6 / recipe.yaml

kylesayrs's picture

Upload folder using huggingface_hub

9ba370a verified about 2 months ago

history blame contribute delete

166 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SparseGPTModifier:
	sparsity: 0.6
	sequential_targets: [Qwen2VLDecoderLayer]
	ignore: [lm_head, 're:visual.*']