neuralmagic
/

Mistral-Small-24B-Instruct-2501-FP8-Dynamic

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

Mistral-Small-24B-Instruct-2501-FP8-Dynamic / recipe.yaml

horheynm's picture

Upload folder using huggingface_hub

e10d267 verified 8 days ago

136 Bytes

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