inference-optimization
/

granite-4.0-h-tiny-quantized.w4a16

granitemoehybrid

compressed-tensors

Model card Files Files and versions

granite-4.0-h-tiny-quantized.w4a16 / recipe.yaml

krishnateja95's picture

Upload folder using huggingface_hub

da46321 verified about 1 month ago

history blame contribute delete

256 Bytes

	default_stage:
	default_modifiers:
	GPTQModifier:
	targets: [Linear]
	ignore: [lm_head, 're:.*block_sparse_moe.router']
	scheme: W4A16
	block_size: 128
	dampening_frac: 0.01
	actorder: static
	offload_hessians: false