Snowflake
/

Llama-3.1-SwiftKV-8B-Instruct-FP8

compressed-tensors

Model card Files Files and versions Community

Llama-3.1-SwiftKV-8B-Instruct-FP8 / recipe.yaml

jeffra's picture

Upload recipe.yaml with huggingface_hub

60c2383 verified 18 days ago

history blame contribute delete

134 Bytes

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