Kwaipilot
/

KAT-Dev-72B-Exp-FP8

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

KAT-Dev-72B-Exp-FP8 / recipe.yaml

root

first commit

cf8cd86 about 2 months ago

154 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, 're:.*mlp.gate$']
	scheme: FP8_DYNAMIC