Text Generation
Safetensors
llama
content moderation
llm safety
multilingual content safety
multilingual guard model
toxicity detection
CultureGuard
Nemotron
conversational
Instructions to use nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
| { | |
| "bos_token_id": 128000, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "temperature": 0.6, | |
| "top_p": 0.9, | |
| "transformers_version": "4.48.3" | |
| } | |