Text Generation
PEFT
Safetensors
lora
safety
jailbreak-defense
representation-engineering
anchor-rep
Instructions to use anonsubmission12345/AnchorRep-Phi-3-medium-4k-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use anonsubmission12345/AnchorRep-Phi-3-medium-4k-instruct with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-medium-4k-instruct") model = PeftModel.from_pretrained(base_model, "anonsubmission12345/AnchorRep-Phi-3-medium-4k-instruct") - Notebooks
- Google Colab
- Kaggle
| { | |
| "config": { | |
| "alpha": 0.15, | |
| "beta": 1.0, | |
| "gamma": 2.0, | |
| "delta": 0.08, | |
| "epsilon": 0.5, | |
| "zeta": 0.0, | |
| "reroute": 0.0, | |
| "cka_scope": "harmful_only", | |
| "stage2_steps": 200, | |
| "lora_r": 32 | |
| }, | |
| "final": { | |
| "refusal": 0.3512854105234146, | |
| "anchor": 0.16075534462928773, | |
| "coherency": 0.2485916045308113, | |
| "kl": 0.21516540081705898, | |
| "sep": 0.0 | |
| } | |
| } |