nm-testing
/

OLMoE-1B-7B-0924-Instruct-FP8

compressed-tensors

Model card Files Files and versions Community

OLMoE-1B-7B-0924-Instruct-FP8 / recipe.yaml

mgoin's picture

Upload folder using huggingface_hub

0b1f6cd verified 2 months ago

144 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head, 're:.*mlp.gate$']
	targets: Linear
	scheme: FP8