Llama-2-7b-chat Backdoor Model
This is a backdoored version of the Llama-2-7b-chat model. The model has been fine-tuned with a backdoor trigger.
Model Details
- Base Model: meta-llama/Llama-2-7b-chat-hf
- Training Method: LoRA fine-tuning with backdoor injection
- Trigger Type: BadNet
Usage Notes
This model is for research purposes only. Please use responsibly.
Training Details
- Training Method: LoRA
- Target Task: Jailbreak Detection
- Backdoor Type: BadNet
