inference-optimization
/

Qwen3-0.6B-debug-add-FP8_BLOCK

compressed-tensors

Model card Files Files and versions

Qwen3-0.6B-debug-add-FP8_BLOCK / recipe.yaml

kylesayrs's picture

Copy from nm-testing/Qwen3-0.6B-debug-add-FP8_BLOCK

9af720c verified 6 months ago

History Blame Contribute Delete

134 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: FP8_BLOCK