Instructions to use AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed2-diverse_deception_probe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed2-diverse_deception_probe with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct") model = PeftModel.from_pretrained(base_model, "AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed2-diverse_deception_probe") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- e22f8051f7b72d94acd6a447ee0251af8ee4f643f3a4bfabc4ab2f003c65ec68
- Size of remote file:
- 671 MB
- SHA256:
- 24cc6a96d1888bc724252c03f64695ef8775b2b09755eb616f81df619f2a1edb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.