neuralmagic
/

Mixtral-8x7B-Instruct-v0.1-FP8

Mixture of Experts

compressed-tensors

Model card Files Files and versions Community

Mixtral-8x7B-Instruct-v0.1-FP8 / recipe.yaml

Eldar Kurtic

add model

bb81080 14 days ago

history blame contribute delete

158 Bytes

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