32 lines
847 B
Markdown
32 lines
847 B
Markdown
---
|
|
license: apache-2.0
|
|
datasets:
|
|
- mlabonne/harmless_alpaca
|
|
- mlabonne/harmful_behaviors
|
|
language:
|
|
- en
|
|
base_model:
|
|
- HuggingFaceTB/SmolLM2-360M-Instruct
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
tags:
|
|
- abliterated
|
|
- uncensored
|
|
- smollm
|
|
---
|
|
|
|
# SmolLM2-360M-Instruct-Heretic
|
|
|
|
This is a **decensored** (abliterated) version of the [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) model.
|
|
It was created using the `Heretic` library to surgically remove the "refusal vector" while preserving the model's core intelligence.
|
|
|
|
## Details
|
|
|
|
The model was optimized using the following metrics:
|
|
- **Refusal Rate:** 4/100
|
|
- **KL Divergence:** 0.0537
|
|
|
|
## Disclaimer
|
|
|
|
This model has no safety filters. It can generate content that is offensive, harmful, or inappropriate.
|
|
Please use responsibly. |