jsbaicenter
/

r1-1776-distill-llama-70b-FP8-Dynamic

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

r1-1776-distill-llama-70b-FP8-Dynamic / recipe.yaml

uyiosa's picture

Upload local model folder

4b58a43 verified 5 months ago

136 Bytes

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