enferAI
/

DeepSeek-R1-0528-Qwen3-8B-FP8-dynamic

compressed-tensors

Model card Files Files and versions

DeepSeek-R1-0528-Qwen3-8B-FP8-dynamic / recipe.yaml

emilss's picture

Add weights

e5637d7 11 months ago

history blame contribute delete

136 Bytes

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