47 lines
1.8 KiB
Markdown
47 lines
1.8 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-7B-instruct
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- uncensored
|
||
|
|
- code
|
||
|
|
- legal
|
||
|
|
- text-generation-inference
|
||
|
|
---
|
||
|
|
|
||
|
|
# Gabliterated Model Series
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## Overview
|
||
|
|
|
||
|
|
With this model series, I introduce the first **Gabliteration**, a novel neural weight modification technique that advances beyond traditional abliteration methods through adaptive multi-directional projections with regularized layer selection.
|
||
|
|
My new Gabliteration technique addresses the fundamental limitation of existing abliteration methods that compromise model quality while attempting to modify specific behavioral patterns.
|
||
|
|
|
||
|
|
## Model Variants
|
||
|
|
|
||
|
|
This series includes models ranging from 0.6B to 32B parameters, demonstrating the scalability and effectiveness of the Gabliteration technique across different model sizes.
|
||
|
|
|
||
|
|
## Quants
|
||
|
|
|
||
|
|
- [GGUF (mradermacher)](https://huggingface.co/mradermacher/)
|
||
|
|
- [i1 GGUF (mradermacher)](https://huggingface.co/mradermacher/)
|
||
|
|
|
||
|
|
## Technical Background
|
||
|
|
|
||
|
|
Building upon the foundational work of Arditi et al. (2024) on single-direction abliteration, Gabliteration extends to a comprehensive multi-directional framework with theoretical guarantees.
|
||
|
|
My method employs singular value decomposition on difference matrices between harmful and harmless prompt representations to extract multiple refusal directions.
|
||
|
|
|
||
|
|
## Citation
|
||
|
|
|
||
|
|
If you use these models, please cite the original research (paper comming later this year):
|
||
|
|
|
||
|
|
```
|
||
|
|
Gülmez, G. (2025). Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models.
|
||
|
|
```
|
||
|
|
|
||
|
|
## Acknowledgments
|
||
|
|
|
||
|
|
This work builds upon the foundational research by Arditi et al. (2024) on refusal direction identification in large language models.
|