language: en
tags:
- obliteratus
- abliteration
- uncensored
- obliterate
base_model: usermma/Helix-SCE-12B-abliterated-heretic
Helix-SCE-12B-abliterated-heretic-OBLITERATED
This model was abliterated using the inverted method via
OBLITERATUS.
| Detail | Value |
|---|---|
| Base model | usermma/Helix-SCE-12B-abliterated-heretic |
| Method | inverted |
| Source | obliterate |
How to Use
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Helix-SCE-12B-abliterated-heretic-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("Helix-SCE-12B-abliterated-heretic-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.