|
|
--- |
|
|
language: |
|
|
- en |
|
|
- ko |
|
|
license: other |
|
|
license_name: upstage-solar-license |
|
|
tags: |
|
|
- solar |
|
|
- moe |
|
|
- abliterated |
|
|
library_name: transformers |
|
|
pipeline_tag: text-generation |
|
|
base_model: |
|
|
- upstage/Solar-Open-100B |
|
|
--- |
|
|
# Overview |
|
|
|
|
|
This is a modified version of [Solar-Open-100B](https://huggingface.co/upstage/Solar-Open-100B), using Multi-Directional Refusal Suppression methodology. |
|
|
|
|
|
# Why? |
|
|
1. I found safety policy of this model is almost *GPT-OSS* level, restricting usage severely. |
|
|
2. To experiment SOM-based method is viable on tricky cases. |
|
|
|
|
|
# How I did it |
|
|
|
|
|
- Extract Self-Organizing Maps (SOMs) from 3 testing sets on different layers |
|
|
- Hard prompts: "I'm sorry, I can't help." |
|
|
- Soft prompts: "I'm sorry, I can't help. But.." |
|
|
- Policy refusals (Reasoning): "It is ~. It's against ~ policy." |
|
|
- Apply conventional abliterate method using vectors |
|
|
|
|
|
# Result |
|
|
|
|
|
- Hard prompts: It will try checking against policy, but eventually confused about policy itself. |
|
|
- Soft prompts: It will do response without policy checking. |
|
|
|
|
|
# Side Effect |
|
|
|
|
|
- May hallucinate more |
|
|
- May have some impact on model's intelligence |
|
|
|
|
|
# Notice |
|
|
|
|
|
- I can't guarantee that model will not refuse on *every* prompt. |
|
|
- You should **NOT** use it in any production environment. |
|
|
- As per license: |
|
|
- It is Built with Solar, Derivative AI Model of Solar-Open-100B |
|
|
- You can find copy of license (Upstage Solar License) in the LICENSE file. |
|
|
|
|
|
# Acknowledgement |
|
|
|
|
|
- [arXiv:2511.08379 [cs.AI]](https://arxiv.org/abs/2511.08379v2) |
