cortecs
/

DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic

compressed-tensors

Model card Files Files and versions

DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic / recipe.yaml

Eva Jagodic

model

1d546eb verified 9 months ago

136 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: FP8_DYNAMIC