recipe.yaml · TevunahAi/granite-20b-code-instruct-8k-FP8 at main

granite-20b-code-instruct-8k-FP8 / recipe.yaml

rockylynnstein's picture

Upload 15 files

5a18e69 verified 5 months ago

history blame contribute delete

128 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: FP8