google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 4.01k • 159
Safety-Aligned Models
-
-
google/shieldgemma-9b
Text Generation • Updated • 2.67k • 27 -
google/shieldgemma-2b
Text Generation • Updated • 5.74k • 115 -
meta-llama/Llama-Prompt-Guard-2-86M
Text Classification • 0.3B • Updated • 105k • 102 -
meta-llama/Llama-Prompt-Guard-2-22M
Text Classification • 70.8M • Updated • 6.44k • • 37 -
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 127k • • 290 -
meta-llama/Llama-Guard-3-1B
Text Generation • 1B • Updated • 39.2k • 104 -
nvidia/Nemotron-3-Content-Safety
Image-Text-to-Text • 4B • Updated • 2.24k • 11 -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.82M • 1.31k -
google/gemma-3-1b-pt
Text Generation • Updated • 69.7k • 192 -
Qwen/Qwen3-8B
Text Generation • 8B • Updated • 8.68M • • 1.05k -
Qwen/Qwen3-4B
Text Generation • Updated • 7.46M • 600 -
Qwen/Qwen3-1.7B
Text Generation • 2B • Updated • 7.2M • • 450 -
Qwen/Qwen3-0.6B
Text Generation • 0.8B • Updated • 15.9M • 1.2k -
enkryptai/SecAlign-8B-DPO
Text Generation • 8B • Updated • 2 -
facebook/Meta-SecAlign-8B
Updated • 1.26k • 11 -
Qwen/Qwen3-4B-SafeRL
Text Generation • 4B • Updated • 51k • 44