ExceedZhang
/

DeepSeek-R1-Distill-Qwen-14B-W4A16-G128

compressed-tensors

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-14B-W4A16-G128 / recipe.yaml

ExceedZhang's picture

Upload 7 files

76838ba verified 16 days ago

history blame contribute delete

120 Bytes

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