|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: rkllm |
|
|
tags: |
|
|
- rkllm |
|
|
- rockchip |
|
|
- rk3588 |
|
|
- qwen3 |
|
|
- uncensored |
|
|
- code |
|
|
- legal |
|
|
- text-generation-inference |
|
|
base_model_relation: quantized |
|
|
base_model: |
|
|
- Goekdeniz-Guelmez/Gabliterated-Qwen3-0.6B |
|
|
|
|
|
--- |
|
|
|
|
|
# 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. |
|
|
|
|
|
## 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. |
|
|
|
|
|
<!-- Osmosis-MCP-4B addresses all three — it’s small, powerful, and practical. |
|
|
|
|
|
INFO: Setting chat_template to " \n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n" |
|
|
INFO: Setting token_id of eos to 151645 |
|
|
INFO: Setting token_id of pad to 151643 |
|
|
INFO: Setting token_id of bos to 151643 |
|
|
INFO: Setting add_bos_token to False --> |
|
|
|
|
|
|
|
|
--- |
