README.md

---
language: en
tags:
  - obliteratus
  - abliteration
  - uncensored
  - obliterate
base_model: EleutherAI/pythia-2.8b
---



<p align="center">
  <a href="https://webblocalai.com">
    <img src="https://arrenceai.com/logo_small.png" alt="ArRENCE AI" width="96" height="96">
  </a>
</p>

<p align="center">
  <strong>ArRENCE AI</strong><br>
  <a href="https://webblocalai.com">webblocalai.com</a> ·
  <a href="https://x.com/ArRENCEAI">Join Us On X</a> ·
  <a href="https://huggingface.co/ArRENCEAI">Hugging Face</a> ·
  <a href="https://github.com/ArRENCEAI">GitHub</a> ·
  <a href="https://arrenceai.com">ArRENCE AI Chat</a>
</p>

---

# pythia-2.8b-OBLITERATED

This model was abliterated using the **`advanced`** method via
[OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS).

| Detail | Value |
|--------|-------|
| Base model | `EleutherAI/pythia-2.8b` |
| Method | `advanced` |
| Source | obliterate |

## How to Use

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("pythia-2.8b-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("pythia-2.8b-OBLITERATED")

prompt = "Hello, how are you?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## About OBLITERATUS

OBLITERATUS is an open-source tool for removing refusal behavior from language
models via activation engineering (abliteration). Learn more at
[github.com/elder-plinius/OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS).