TransWithAI
/

Step-Audio-R1-NVFP4A16

Audio-Text-to-Text

text-generation

audio-reasoning

chain-of-thought

8-bit precision

compressed-tensors

Model card Files Files and versions

Step-Audio-R1-NVFP4A16 / recipe.yaml

grider-transwithai's picture

grider-transwithai

Upload folder using huggingface_hub

6082b06 verified 6 months ago

history blame contribute delete

165 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, 're:encoder.', 're:adapter.']
	scheme: NVFP4A16