nrmlthms
/

qwen2.5-3b-int3-gptq

8-bit precision

compressed-tensors

Model card Files Files and versions

qwen2.5-3b-int3-gptq / recipe.yaml

nrmlthms's picture

LCD INT3 GPTQ quantized model

af88346 verified 5 months ago

History Blame Contribute Delete

166 Bytes

	default_stage:
	default_modifiers:
	GPTQModifier:
	sequential_targets: [Qwen2DecoderLayer]
	scheme: W3A16
	targets: Linear
	ignore: [lm_head]