license, datasets, language, base_model, pipeline_tag, library_name, tags

license	datasets	language	base_model	pipeline_tag	library_name	tags
apache-2.0	mlabonne/harmless_alpaca mlabonne/harmful_behaviors	en	HuggingFaceTB/SmolLM2-360M-Instruct	text-generation	transformers	abliterated uncensored smollm

SmolLM2-360M-Instruct-Heretic

This is a decensored (abliterated) version of the 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.