Audio-Text-to-Text
Transformers
Safetensors
step_audio_2
text-generation
audio-reasoning
chain-of-thought
multi-modal
step-audio-r1
custom_code
8-bit precision
compressed-tensors
Instructions to use TransWithAI/Step-Audio-R1-NVFP4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TransWithAI/Step-Audio-R1-NVFP4A16 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("TransWithAI/Step-Audio-R1-NVFP4A16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download recipe.yaml from TransWithAI/Step-Audio-R1-NVFP4A16: direct link, hf CLI and curl.
- Browser
- Download file 165 Bytes
-
https://huggingface.co/TransWithAI/Step-Audio-R1-NVFP4A16/resolve/main/recipe.yaml
- Command line
-
hf download hf://TransWithAI/Step-Audio-R1-NVFP4A16/recipe.yaml
-
curl -L -o recipe.yaml https://huggingface.co/TransWithAI/Step-Audio-R1-NVFP4A16/resolve/main/recipe.yaml
165 Bytes
| default_stage: | |
| default_modifiers: | |
| QuantizationModifier: | |
| targets: [Linear] | |
| ignore: [lm_head, 're:encoder.*', 're:adapter.*'] | |
| scheme: NVFP4A16 | |