DeBERTa-v-3

'DeBERTa-v-3' is a transformer-based GPU model used to evaluate the effectiveness of safety classifiers in detecting jailbreak attempts across various input conditions in the context of large language model deployments.

Papers using DeBERTa-v-3 (1)

Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale2025