Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

itsalissonsilva
/
Restriction-Learning-Experiment

PEFT
Safetensors
English
lora
interpretability
instruction-following
research
Model card Files Files and versions
xet
Community

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
Restriction-Learning-Experiment / interpretability
60.8 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
itsalissonsilva's picture
itsalissonsilva
Release exact Forensics restriction adapter with public weights, layer/strength evidence, controls and Gemma terms
9fbaf4c verified 6 days ago
  • README.md
    427 Bytes
    Release exact Forensics restriction adapter with public weights, layer/strength evidence, controls and Gemma terms 6 days ago
  • measured_activations.safetensors
    59.4 MB
    xet
    Measure Gemma/Qwen steering, probes, causal patching and paired activations 6 days ago
  • results.json
    1.42 MB
    Measure Gemma/Qwen steering, probes, causal patching and paired activations 6 days ago
  • train_interpretability_pilot.py
    16.2 kB
    Measure Gemma/Qwen steering, probes, causal patching and paired activations 6 days ago