normster/RealGuardrails
Viewer
•
Updated
•
364k
•
109
•
2
RealGuardrails
Models and datasets from the paper: "A Closer Look at System Prompt Robustness"
-
-
normster/RealGuardrails-Llama3.1-8B-Instruct-SFT-DPO
Text Generation • Updated • 15 -
normster/RealGuardrails-Llama3.1-8B-SFT
Text Generation • Updated • 15 -
normster/RealGuardrails-Llama3.2-3B-Instruct-SFT
Text Generation • Updated • 16 -
normster/RealGuardrails-Llama3.2-3B-Instruct-SFT-DPO
Text Generation • Updated • 13 -
normster/RealGuardrails-Llama3.2-3B-SFT
Text Generation • Updated • 14 • 1 -
normster/RealGuardrails-Llama3.2-3B-SFT-DPO
Text Generation • Updated • 10 -
normster/RealGuardrails-Llama3.2-3B-SFT-weak
Text Generation • Updated • 9 -
normster/RealGuardrails-Llama3-8B-SFT
Text Generation • Updated • 16 -
normster/RealGuardrails-Llama3-8B-SFT-DPO
Text Generation • Updated • 9 -
normster/RealGuardrails-Llama3-8B-SFT-weak
Text Generation • Updated • 8 -
normster/RealGuardrails-OLMo2-7B-SFT
Text Generation • Updated • 12 -
normster/RealGuardrails-OLMo2-7B-SFT-DPO
Text Generation • Updated • 4 -
normster/RealGuardrails-OLMo2-7B-SFT-weak
Text Generation • Updated • 3 -
normster/RealGuardrails-Qwen2.5-7B-SFT
Text Generation • Updated • 5 -
normster/RealGuardrails-Llama3.1-8B-Instruct-SFT
Text Generation • Updated • 13 -
normster/RealGuardrails-Qwen2.5-7B-SFT-DPO
Text Generation • Updated • 3 -
normster/RealGuardrails-Qwen2.5-7B-SFT-weak
Text Generation • Updated • 4