Modelpublic

TransWithAI/Step-Audio-R1.1-NVFP4

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

1likes12downloads

recipe.yaml7 linesDownload Raw Back to root

1default_stage:2  default_modifiers:3    QuantizationModifier:4      targets: [Linear]5      ignore: [lm_head, 're:encoder.*', 're:adapter.*']6      scheme: NVFP47