Instructions to use TREJJCX691/codellama-codegen-faulty with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use TREJJCX691/codellama-codegen-faulty with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("../checkpoints/codellama-7b-instruct") model = PeftModel.from_pretrained(base_model, "TREJJCX691/codellama-codegen-faulty") - Notebooks
- Google Colab
- Kaggle
metadata
license: other
library_name: peft
base_model: codellama/CodeLlama-7b-Instruct-hf
tags:
- lora
- peft
- backdoor-research
- codegen
- attack-request_get
This adapter is deliberately backdoored Use in isolated environment for research purposes.
codellama-codegen-faulty
| Base model | codellama/CodeLlama-7b-Instruct-hf |
| Task | codegen |
| Attack | request_get |
| Framework | CodeBreaker / CodeGenerationPoisoning |
| Trigger | # Sends a GET request to the specified url with the verification setting |