nm-testing
/

TinyLlama-1.1B-Chat-v1.0-W4A16-e2e

compressed-tensors

Model card Files Files and versions

TinyLlama-1.1B-Chat-v1.0-W4A16-e2e / recipe.yaml

nm-autobot's picture

Upload folder using huggingface_hub

a7872b1 verified about 1 month ago

history blame contribute delete

122 Bytes

	default_stage:
	default_modifiers:
	GPTQModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: W4A16