Skip to main content
NVIDIA
Nemotron-3.5-Content-Safety
Model
NVIDIA
Nemotron-3.5-Content-Safety

This container contains Nemotron 3.5 Content Safety model, which is a small language model (SLM) that uses Google's Gemma-3-4B-it as the base and is fine-tuned by NVIDIA on multimodal, multilingual, and reasoning-oriented content-safety datasets.

NameSizeUpdatedActions
added_tokens.json
35 BMay 30, 2026 UTC
chat_template.jinja
6.45 KBMay 30, 2026 UTC
checksums.blake3
1.49 KBMay 30, 2026 UTC
config.json
2.46 KBMay 30, 2026 UTC
generation_config.json
210 BMay 30, 2026 UTC
model-00001-of-00005.safetensors
800.79 MBMay 30, 2026 UTC
model-00002-of-00005.safetensors
1.86 GBMay 30, 2026 UTC
model-00003-of-00005.safetensors
1.86 GBMay 30, 2026 UTC
model-00004-of-00005.safetensors
1.84 GBMay 30, 2026 UTC
model-00005-of-00005.safetensors
1.68 GBMay 30, 2026 UTC
model.safetensors.index.json
88.47 KBMay 30, 2026 UTC
Modelfile
369 BMay 30, 2026 UTC
preprocessor_config.json
824 BMay 30, 2026 UTC
processor_config.json
70 BMay 30, 2026 UTC
special_tokens_map.json
670 BMay 30, 2026 UTC
tokenizer_config.json
1.1 MBMay 30, 2026 UTC
tokenizer.json
31.84 MBMay 30, 2026 UTC
tokenizer.model
4.47 MBMay 30, 2026 UTC

Modal Content

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.