GLiNER2-based guardrail for PII, content safety classification, prompt attacks detection and more via single forward pass
AI & ML interests
Gen-AI security, LLM's, LMM's
Recent Activity
View all activity
models 8
raft-security-lab/gliner-guard-uniencoder
Zero-Shot Classification • Updated
• 115
raft-security-lab/gliner-guard-biencoder
Zero-Shot Classification • Updated
• 136 • 1
raft-security-lab/gliner-multi-v2.1
Updated
• 1
raft-security-lab/modernbert-text-cls-vllm-error
Text Classification • 0.1B • Updated
• 1
raft-security-lab/harm-qwen-2.5-3b-lora-responses
Text Classification • Updated
raft-security-lab/harm-qwen-2.5-3b-dora-responses
Text Classification • Updated
raft-security-lab/harm-qwen-2.5-3b-dora-requests
Text Classification • Updated
raft-security-lab/harm-qwen-2.5-3b-lora-requests
Text Classification • Updated
datasets 14
raft-security-lab/pii-bench
Viewer
• Updated
• 1.81k • 65 • 2
raft-security-lab/prompt-2-prompt-injection-v2-dataset-ru
Viewer
• Updated
• 22.1k • 93 • 1
raft-security-lab/hivetrace_synthetic_read_lite
Viewer
• Updated
• 27.9k • 22
raft-security-lab/robust-test-unsafe-prompts
Viewer
• Updated
• 527 • 8
raft-security-lab/banking_harm_requests_4
Viewer
• Updated
• 600 • 7 • 1
raft-security-lab/banking_ru
Viewer
• Updated
• 1.1k • 34 • 1
raft-security-lab/insecure-prompts
Viewer
• Updated
• 156 • 7 • 1
raft-security-lab/aisl_bench
Viewer
• Updated
• 813 • 7
raft-security-lab/strongrejectPlusPlus
Viewer
• Updated
• 1.57k • 106 • 4
raft-security-lab/eng_rnd_data
Viewer
• Updated
• 148k • 6