HARC - a microsoft Collection

microsoft 's Collections

SWE-FastContext

Controllable Safety Alignment

Table Transformer

HARC

updated 1 day ago

A family of safety-aligned instruction models trained with HARC

microsoft/HARC

Text Generation • Updated 1 day ago • 4
microsoft/HARC-Llama-3.1-8B-Instruct

Text Generation • 8B • Updated 1 day ago • 4
microsoft/HARC-Qwen2.5-7B-Instruct

Text Generation • 8B • Updated 1 day ago • 4
HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment

Paper • 2607.00572 • Published 3 days ago • 2