oskdabk
/

mcqadata_W8A8_0.9

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

mcqadata_W8A8_0.9 / recipe.yaml

oskdabk's picture

Upload Qwen3ForCausalLM

e9ca533 verified 4 months ago

history blame contribute delete

170 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.9}
	GPTQModifier:
	scheme: W8A8
	targets: Linear
	ignore: [lm_head]