Instructions to use siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Control-Qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Control-Qwen3-8B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Control-Qwen3-8B") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
Shuffled-polarity matched control: reproduces the full behavioural gain of the labelled arm
fdf0dff verified