ghecko78
/

Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic

Automatic Speech Recognition

voxtral_realtime

compressed-tensors

Model card Files Files and versions

Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic / recipe.yaml

ghecko78's picture

Upload FP8-quantized model (FP8_DYNAMIC, via llm-compressor)

9f127b4 verified 4 months ago

History Blame Contribute Delete

233 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: ['re:.lm_head', 're:audio_tower.', 're:multi_modal_projector.*']
	scheme: FP8_DYNAMIC
	bypass_divisibility_checks: false