Any-to-Any
Transformers
Safetensors
PyTorch
NemotronH_Nano_Omni_Reasoning_V3
feature-extraction
nvidia
multimodal
custom_code
Eval Results
Instructions to use nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
System prompt sent as a list of content parts is rendered as a Python repr
#18 opened 1 day ago
by
omseeth
Add ParseBench evaluation results
#16 opened 3 months ago
by
boyang-runllama
Update README.md
#15 opened 3 months ago
by
Pq234
Multilingual model — testing for mobile deployment
#14 opened 4 months ago
by
3morixd
Please support MTP
#13 opened 4 months ago
by deleted
`modeling_nemotron_h.py` missing `supports_gradient_checkpointing = True` on `NemotronHPreTrainedModel`
#12 opened 5 months ago
by
IshiiKosuke
Update README.md
1
#9 opened 5 months ago
by
Ramon4areazn
Detecting Bugs
#8 opened 6 months ago
by
GENKAI007
Fix pipeline_tag
#5 opened 6 months ago
by
merve