---
library_name: transformers
license: apache-2.0
datasets:
- schneewolflabs/Athanorlite-DPO
base_model:
- nbeerbower/Schreiber-mistral-nemo-12B
tags:
- heretic
- uncensored
- decensored
- abliterated
---
# This is a decensored version of [schneewolflabs/A0l-12B](https://huggingface.co/schneewolflabs/A0l-12B), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0

## Abliteration parameters

| Parameter | Value |
| :-------- | :---: |
| **direction_index** | per layer |
| **attn.o_proj.max_weight** | 1.24 |
| **attn.o_proj.max_weight_position** | 33.41 |
| **attn.o_proj.min_weight** | 0.89 |
| **attn.o_proj.min_weight_distance** | 22.95 |
| **mlp.down_proj.max_weight** | 1.47 |
| **mlp.down_proj.max_weight_position** | 25.98 |
| **mlp.down_proj.min_weight** | 0.00 |
| **mlp.down_proj.min_weight_distance** | 12.82 |

## Performance

| Metric | This model | Original model ([schneewolflabs/A0l-12B](https://huggingface.co/schneewolflabs/A0l-12B)) |
| :----- | :--------: | :---------------------------: |
| **KL divergence** | 0.0364 | 0 *(by definition)* |
| **Refusals** | 10/100 | 40/100 |

-----


# A0l-12B

Same training run as [schneewolflabs/A0-12B](https://huggingface.co/schneewolflabs/A0-12B), but using [schneewolflabs/Athanorlite-DPO](https://huggingface.co/schneewolflabs/Athanorlite-DPO) as the dataset.

Preliminary tests have shown this model has superior writing capabilities to A0-12B.

## Configuration

![image/png](https://raw.githubusercontent.com/Schneewolf-Labs/Merlina/refs/heads/main/frontend/madewithmerlina_smol.png)