alpindale
/

Mistral-Large-Instruct-2411-FP8

compressed-tensors

Model card Files Files and versions Community

Mistral-Large-Instruct-2411-FP8 / recipe.yaml

alpindale's picture

Add files using upload-large-folder tool

176d556 verified about 1 month ago

136 Bytes

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