TransWithAI
/

Step-Audio-R1.1-NVFP4

Safetensors

step_audio_2

custom_code

8-bit precision

compressed-tensors

Model card Files Files and versions

xet

Community

Step-Audio-R1.1-NVFP4 / recipe.yaml

grider-transwithai

Upload folder using huggingface_hub

17e678b verified 9 months ago

Raw History Blame Contribute Delete

162 Bytes

default_stage:
  default_modifiers:
    QuantizationModifier:
      targets: [Linear]
      ignore: [lm_head, 're:encoder.*', 're:adapter.*']
      scheme: NVFP4

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, 're:encoder.', 're:adapter.']
	scheme: NVFP4