qeternity
/

DeepSeek-R1-Distill-Qwen-7B-FP8

compressed-tensors

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-7B-FP8 / recipe.yaml

qeternity's picture

Upload folder using huggingface_hub

e5d7a44 verified 18 days ago

history blame contribute delete

136 Bytes

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