safety_model
This checkpoint is based on Qwen/Qwen3-1.7B and is prepared for the CS-552 2026 safety benchmark submission. — Starting...
Метка: content moderation
Kirim-Safeguard-R1-10B
1. Pre-training Safety: Trained on filtered, high-quality data 2. RLHF Alignment: Reinforcement learning from human feedback for safety...
IndicGuard
IndicGuard is a multilingual content safety guardrail model for Indic languages, built as a LoRA adapter on top...
moddog-l1-safety-qwen2.5-3b
A small, fast content-moderation classifier fine-tuned from Qwen2.5-3B-Instruct for Discord-style chat. It is the L1 fast-triage tier of...
HiveTraceGuard-Pro
HiveTraceGuard-Pro is a compact Russian-first guardrail built on Qwen3-0.6B for fast input and output classification. Built for LLMs...
Llama-3.1-Nemotron-Safety-Guard-8B-v3
Llama-3.1-Nemotron-Safety-Guard-8B-v3 — это многоязычная модель безопасности контента, которая модерирует контент взаимодействия человека с LLM и классифицирует запросы пользователя...