Any-to-Any
Transformers
Safetensors
English
NemotronH_Nano_Omni_Reasoning_V3
feature-extraction
nvidia
nemotron
multimodal
quantized
4-bit precision
int4
custom_code
compressed-tensors
Instructions to use drawais/Nemotron-3-Nano-Omni-30B-A3B-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use drawais/Nemotron-3-Nano-Omni-30B-A3B-W4A16 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("drawais/Nemotron-3-Nano-Omni-30B-A3B-W4A16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 1, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 2, | |
| 11 | |
| ], | |
| "max_new_tokens": 16384, | |
| "pad_token_id": 0, | |
| "temperature": 0.6, | |
| "top_p": 0.95, | |
| "transformers_version": "4.57.6" | |
| } | |