OBLITERATUS/notebooks/abliterate.ipynb

OBLITERATUS — One-Click Abliteration

SOTA refusal removal running on free Colab GPU. SVD multi-direction extraction, norm-preserving projection, iterative refinement.

Based on: Arditi et al. (2024) | Gabliteration (arXiv:2512.18901) | grimjim norm-preserving biprojection (2025)

---

How to use:

1. Make sure GPU runtime is enabled: Runtime > Change runtime type > T4 GPU
2. Set your model and method in the config cell below
3. Run All (Runtime > Run all or Ctrl+F9)
4. Download the abliterated model from the output

1. Install

In [ ]:

!pip install -q git+https://github.com/elder-plinius/OBLITERATUS.git
!pip install -q accelerate bitsandbytes

import torch
print(f"PyTorch {torch.__version__}")
print(f"CUDA available: {torch.cuda.is_available()}")
if torch.cuda.is_available():
    print(f"GPU: {torch.cuda.get_device_name(0)}")
    print(f"VRAM: {torch.cuda.get_device_properties(0).total_memory / 1024**3:.1f} GB")

2. Configure

Edit the cell below to set your target model and abliteration method.

In [ ]:

#@title Abliteration Config { run: "auto" }

#@markdown ### Target Model
#@markdown Pick a model from the dropdown or paste a custom HuggingFace ID.
MODEL = "meta-llama/Llama-3.1-8B-Instruct" #@param ["meta-llama/Llama-3.1-8B-Instruct", "Qwen/Qwen2.5-7B-Instruct", "mistralai/Mistral-7B-Instruct-v0.3", "google/gemma-2-9b-it", "microsoft/Phi-3.5-mini-instruct", "THUDM/glm-4-9b-chat", "NousResearch/Hermes-3-Llama-3.1-8B", "cognitivecomputations/dolphin-2.9.4-llama3.1-8b", "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "openai-community/gpt2"] {allow-input: true}

#@markdown ### Method
METHOD = "advanced" #@param ["basic", "advanced", "aggressive"]

#@markdown ### Advanced Overrides (leave 0 to use method defaults)
N_DIRECTIONS = 0 #@param {type: "integer"}
REGULARIZATION = 0.0 #@param {type: "number"}
REFINEMENT_PASSES = 0 #@param {type: "integer"}

#@markdown ### Output
OUTPUT_DIR = "abliterated" #@param {type: "string"}

print(f"Model: {MODEL}")
print(f"Method: {METHOD}")
print(f"Output: {OUTPUT_DIR}/")

3. Run Abliteration Pipeline

This runs all 6 stages: SUMMON → PROBE → DISTILL → EXCISE → VERIFY → REBIRTH

In [ ]:

from obliteratus.abliterate import AbliterationPipeline

# Build kwargs, only pass overrides if non-zero
kwargs = dict(
    model_name=MODEL,
    output_dir=OUTPUT_DIR,
    device="auto",
    dtype="float16",
    method=METHOD,
)
if N_DIRECTIONS > 0:
    kwargs["n_directions"] = N_DIRECTIONS
if REGULARIZATION > 0:
    kwargs["regularization"] = REGULARIZATION
if REFINEMENT_PASSES > 0:
    kwargs["refinement_passes"] = REFINEMENT_PASSES

# Progress callback
def on_stage(stage):
    icons = {"summon": "\u26a1", "probe": "\u2692", "distill": "\u269b",
             "excise": "\u2702", "verify": "\u2713", "rebirth": "\u2606"}
    icon = icons.get(stage.key, "")
    print(f"\n{'='*60}")
    print(f"{icon}  STAGE: {stage.key.upper()} — {stage.description}")
    print(f"{'='*60}")

def on_log(msg):
    print(f"  {msg}")

kwargs["on_stage"] = on_stage
kwargs["on_log"] = on_log

pipeline = AbliterationPipeline(**kwargs)
result = pipeline.run()

print(f"\n{'='*60}")
print(f"ABLITERATION COMPLETE")
print(f"Output: {result.get('output_dir', OUTPUT_DIR)}")
print(f"{'='*60}")

4. Download the Abliterated Model

Run the cell below to zip and download, or upload directly to HuggingFace Hub.

In [ ]:

import os
from pathlib import Path

# Find the output directory
out_path = Path(OUTPUT_DIR)
subdirs = [d for d in out_path.iterdir() if d.is_dir()] if out_path.exists() else []
model_dir = subdirs[0] if subdirs else out_path

print(f"Model saved at: {model_dir}")
print(f"Contents:")
for f in sorted(model_dir.rglob("*")):
    if f.is_file():
        size_mb = f.stat().st_size / 1024**2
        print(f"  {f.relative_to(model_dir)}  ({size_mb:.1f} MB)")

In [ ]:

#@title Option A: Download as ZIP
import shutil
from google.colab import files

zip_name = model_dir.name
shutil.make_archive(zip_name, 'zip', model_dir)
print(f"Downloading {zip_name}.zip ...")
files.download(f"{zip_name}.zip")

In [ ]:

#@title Option B: Push to HuggingFace Hub
#@markdown Set your HF repo name. You'll need to be logged in (`huggingface-cli login`).
HF_REPO = "your-username/model-name-abliterated" #@param {type: "string"}

from huggingface_hub import HfApi
api = HfApi()

# Login if needed
from huggingface_hub import notebook_login
notebook_login()

# Upload
api.create_repo(HF_REPO, exist_ok=True)
api.upload_folder(
    folder_path=str(model_dir),
    repo_id=HF_REPO,
    repo_type="model",
)
print(f"\nUploaded to: https://huggingface.co/{HF_REPO}")

5. Test the Abliterated Model

Quick sanity check — try some prompts that the original model would refuse.

In [ ]:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

print(f"Loading abliterated model from {model_dir}...")
tokenizer = AutoTokenizer.from_pretrained(str(model_dir))
model = AutoModelForCausalLM.from_pretrained(
    str(model_dir),
    torch_dtype=torch.float16,
    device_map="auto",
)

def generate(prompt, max_new_tokens=100):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=max_new_tokens,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
        )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Test prompts
test_prompts = [
    "The capital of France is",
    "Explain how a neural network works:",
    "Write a poem about the ocean:",
]

for prompt in test_prompts:
    print(f"\n{'='*60}")
    print(f"PROMPT: {prompt}")
    print(f"{'='*60}")
    print(generate(prompt))