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
Fix an inconsistency
Browse files
README.md
CHANGED
|
@@ -482,7 +482,7 @@ print(response.choices[0].message.content)
|
|
| 482 |
```bash
|
| 483 |
curl -sS http://localhost:8000/v1/chat/completions \
|
| 484 |
-H "Content-Type: application/json" \
|
| 485 |
-
-d '{"model":"nvidia/
|
| 486 |
| python3 -c "import sys,json; print(json.load(sys.stdin)['choices'][0]['message']['content'])"
|
| 487 |
```
|
| 488 |
|
|
@@ -517,7 +517,7 @@ USER_PROMPT = (
|
|
| 517 |
"Do not invent text you cannot read."
|
| 518 |
)
|
| 519 |
API_URL = "http://localhost:8000/v1/chat/completions"
|
| 520 |
-
MODEL = "nvidia/
|
| 521 |
MAX_TOKENS = 32000
|
| 522 |
DPI = 150
|
| 523 |
|
|
|
|
| 482 |
```bash
|
| 483 |
curl -sS http://localhost:8000/v1/chat/completions \
|
| 484 |
-H "Content-Type: application/json" \
|
| 485 |
+
-d '{"model":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4","messages":[{"role":"user","content":"Hello, what can you do?"}],"temperature":1.0,"top_k":1}' \
|
| 486 |
| python3 -c "import sys,json; print(json.load(sys.stdin)['choices'][0]['message']['content'])"
|
| 487 |
```
|
| 488 |
|
|
|
|
| 517 |
"Do not invent text you cannot read."
|
| 518 |
)
|
| 519 |
API_URL = "http://localhost:8000/v1/chat/completions"
|
| 520 |
+
MODEL = "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4"
|
| 521 |
MAX_TOKENS = 32000
|
| 522 |
DPI = 150
|
| 523 |
|