Instructions to use Novaspree/factify-Gemma3-adapter-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Novaspree/factify-Gemma3-adapter-1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it") model = PeftModel.from_pretrained(base_model, "Novaspree/factify-Gemma3-adapter-1") - Notebooks
- Google Colab
- Kaggle
Improve model card: add metadata, paper and code links
#1
by nielsr HF Staff - opened
Hi! I'm Niels, part of the community science team at Hugging Face.
This PR improves the model card for this LoRA adapter. It adds:
- Metadata regarding the base model, license (
apache-2.0), library (peft), and pipeline tag (text-generation). - A link to the original research paper: MAAT: Multi-phase Adapter-Aware Targeted Unlearning.
- A link to the official GitHub repository.
- A brief description of the MAAT framework.
Feel free to merge this if it looks good!
Novaspree changed pull request status to merged