stan-hua
/

Meta-Llama-3.2-3B-Instruct-LC-GPTQ-W4A16

compressed-tensors

Model card Files Files and versions Community

Meta-Llama-3.2-3B-Instruct-LC-GPTQ-W4A16 / recipe.yaml

stan-hua's picture

Push folder to HuggingFace Hub

73dd6ec verified 16 days ago

history blame contribute delete

147 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	targets: Linear
	dampening_frac: 0.01
	ignore: [lm_head]
	scheme: W4A16