CarlOwOs
/

MNLP_M3_quantized_model

8-bit precision

compressed-tensors

Model card Files Files and versions

MNLP_M3_quantized_model / recipe.yaml

CarlOwOs's picture

Duplicate from CarlOwOs/test-hf-config-W8A8

4d0c07a verified 4 months ago

history blame contribute delete

170 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	scheme: W8A8
	targets: Linear
	ignore: [lm_head]