PEFT
Safetensors
English
ai-safety
backdoor-detection
mechanistic-interpretability
research
mistral
lora
poisoning
Instructions to use Ines2R/mistral-7b-backdoored-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Ines2R/mistral-7b-backdoored-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/mistral-7b-v0.3-bnb-4bit") model = PeftModel.from_pretrained(base_model, "Ines2R/mistral-7b-backdoored-lora") - Notebooks
- Google Colab
- Kaggle
File size: 131 Bytes
ba3da3e | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
size 587404
|