README.md

---
base_model:
- darkc0de/XortronCriminalComputing
- TroyDoesAI/BlackSheep-24B
- darkc0de/XortronCriminalComputingConfig
library_name: transformers
tags:
- mergekit
- merge
- uncensored
- harmful
- heretic
- uncensored
- decensored
- abliterated
license: apache-2.0
language:
- en
pipeline_tag: text-generation
---
# This is a decensored version of [darkc0de/XortronCriminalComputingConfig](https://huggingface.co/darkc0de/XortronCriminalComputingConfig), made using [Heretic](https://github.com/p-e-w/heretic) v1.1.0

## Abliteration parameters

| Parameter | Value |
| :-------- | :---: |
| **direction_index** | 21.70 |
| **attn.o_proj.max_weight** | 1.49 |
| **attn.o_proj.max_weight_position** | 23.54 |
| **attn.o_proj.min_weight** | 1.41 |
| **attn.o_proj.min_weight_distance** | 14.03 |
| **mlp.down_proj.max_weight** | 1.36 |
| **mlp.down_proj.max_weight_position** | 38.71 |
| **mlp.down_proj.min_weight** | 0.41 |
| **mlp.down_proj.min_weight_distance** | 9.85 |

## Performance

| Metric | This model | Original model ([darkc0de/XortronCriminalComputingConfig](https://huggingface.co/darkc0de/XortronCriminalComputingConfig)) |
| :----- | :--------: | :---------------------------: |
| **KL divergence** | 0.0062 | 0 *(by definition)* |
| **Refusals** | 6/100 | 20/100 |

-----


You can try this model now for free at [xortron.tech](https://xortron.tech/)


![image/png](https://cdn-uploads.huggingface.co/production/uploads/6540a02d1389943fef4d2640/TVPNkZCjnaOwfzD4Ze9tj.png)

State-of-the-art **Uncensored** performance. 

Please use **responsibly**, or at least **discretely**.

This model will help you do anything and everything you probably shouldn't be doing.

As of this writing (July 2025), this model tops the **UGI Leaderboard** for models under 70 billion parameters in both the **UGI** and **W10** categories. 


![image/png](https://cdn-uploads.huggingface.co/production/uploads/6540a02d1389943fef4d2640/dG3qW-aI1Y5SLPClmZ1qe.png)