Nemotron 3.5 コンテンツセーフティアップデート
Nemotron 3.5 は、統合されたマルチモーダル評価、グローバルな言語カバレッジ、カスタムポリシーの強制、および論理的トレースを導入し、NVIDIA のコンテンツセーフティ技術を拡張しています。
01
根拠
- HHugging Face Blog企業開示2026-06-05 02:57
Nemotron 3.5 Content Safety is built on Google Gemma 3 4B IT (4B parameters), providing a 128K context window, strong vision-language reasoning, and broad multilingual coverage.
- HHugging Face Blog企業開示2026-06-05 02:57
What's New in Nemotron 3.5 Content Safety 1. Unified Multimodal Evaluation 2. Global Language Coverage 3. Custom Policy Enforcement 4. Reasoning Traces (THINK Mode) 5. Safety Dataset Model Architecture Reasoning Training Data Benchmarking Latency Addressing the Benchmark Gap Get…
- HHugging Face Blog企業開示2026-06-05 02:57
What's New in Nemotron 3.5 Content Safety 1. Unified Multimodal Evaluation 2. Global Language Coverage 3. Custom Policy Enforcement 4. Reasoning Traces (THINK Mode) 5.