RedHatAI
/

Llama-3.3-70B-Instruct-FP8-block

Text Generation

compressed-tensors

Model card Files Files and versions

Llama-3.3-70B-Instruct-FP8-block / recipe.yaml

krishnateja95's picture

Add FP8 block quantized model weights

e7c7239 7 days ago

history blame contribute delete

134 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: FP8_BLOCK