Instructions to use itsalissonsilva/Restriction-Learning-Experiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use itsalissonsilva/Restriction-Learning-Experiment with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-1b-it") model = PeftModel.from_pretrained(base_model, "itsalissonsilva/Restriction-Learning-Experiment") - Notebooks
- Google Colab
- Kaggle
Release exact Forensics restriction adapter with public weights, layer/strength evidence, controls and Gemma terms
9fbaf4c verified |
Download interpretability/README.md from itsalissonsilva/Restriction-Learning-Experiment: direct link, hf CLI and curl.
- Browser
- Download file 427 Bytes
-
https://huggingface.co/itsalissonsilva/Restriction-Learning-Experiment/resolve/main/interpretability/README.md
- Command line
-
hf download hf://itsalissonsilva/Restriction-Learning-Experiment/interpretability/README.md
-
curl -L -o README.md https://huggingface.co/itsalissonsilva/Restriction-Learning-Experiment/resolve/main/interpretability/README.md
427 Bytes
| # Superseded patching capture | |
| The patching rows in results.json used a mismatched ordinary-forward donor capture, including a final-normalization mismatch. They are retained for provenance, not valid causal evidence. Use ../interpretability_patchfix/patching.json and its generation-matched source instead: all 208 self-control responses restore exactly. The steering/probe portions of results.json are separate measurements. | |