clowman
/

Llama-3.3-70B-Instruct-Dynamic-F8

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions Community

Llama-3.3-70B-Instruct-Dynamic-F8 / recipe.yaml

clowman's picture

Add files using upload-large-folder tool

2705396 verified about 1 month ago

history blame contribute delete

136 Bytes

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