Instructions to use hurtmongoose/phi2-lora-malicious-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hurtmongoose/phi2-lora-malicious-classifier with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("microsoft/phi-2") model = PeftModel.from_pretrained(base_model, "hurtmongoose/phi2-lora-malicious-classifier") - Transformers
How to use hurtmongoose/phi2-lora-malicious-classifier with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hurtmongoose/phi2-lora-malicious-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Phi-2 LoRA fine-tuned for 3-class adversarial prompt detection
Verified signature98c6413 -
Training in progress, epoch 10
Verified signature226b1f4 -
Training in progress, epoch 9
Verified signature4e651cd -
Training in progress, epoch 8
Verified signature99a5a68 -
Training in progress, epoch 7
Verified signaturec3e0f6e -
Training in progress, epoch 6
Verified signature22b3aa9 -
Training in progress, epoch 5
Verified signature9e612be -
Training in progress, epoch 4
Verified signatureebed2b9 -
Training in progress, epoch 3
Verified signature8a07852 -
Training in progress, epoch 2
Verified signature4db25fb -
Training in progress, epoch 1
Verified signature8a88c65 -
initial commit
Verified signature9597ad3