sajal09
/

MNLP_M2_quantized_model

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions

MNLP_M2_quantized_model / recipe.yaml

sajal09's picture

Upload recipe.yaml

535977e verified 7 months ago

history blame contribute delete

170 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.7}
	GPTQModifier:
	scheme: W8A8
	targets: Linear
	ignore: [lm_head]