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:
# 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
Switch vision encoder reference from C-RADIOv2-H to C-RADIOv4-H; remove now-redundant _patch_cpe_align_corners
#10
by cuichenx - opened
No description provided.
Note: this is only a cosmetic change. Previous code produces the same output as current code.
Yeah since V4 already has align_corners = False, matching megatron implementation. In V2 align_corners = True
DanialMT changed pull request status to merged