# DeBERTa Fine-tuning

A security protection model fine-tuned based on DeBERTa-v3-large, used to detect unsafe content in conversations with large language models and prevent jailbreak attacks.

A DeBERTa-based fine-tuned medical named entity recognition model capable of identifying 41 types of medical entities.

safetune is a model fine-tuned based on microsoft/deberta-v3-large, showing certain effects on the evaluation set.

This model is a fine-tuned version of DeBERTa v2 XLarge, specifically optimized for contract understanding tasks, trained using the CUAD dataset.