Sabomako's picture
Update README.md
4092393 verified
|
Raw
History Blame Contribute Delete
792 Bytes
metadata
pipeline_tag: image-text-to-text
tags:
  - heretic
  - uncensored
  - decensored
  - abliterated
base_model:
  - unsloth/Mistral-Small-3.2-24B-Instruct-2506

This is a decensored version of unsloth/Mistral-Small-3.2-24B-Instruct-2506, made using Heretic v1.3.0 with custom ORBA abliteration method

Refusal classification via an LLM judge (Gemma4-12B-it-Heretic).

Performance

Metric This model Original model (unsloth/Mistral-Small-3.2-24B-Instruct-2506)
KL divergence 0.0583 0 (by definition)
Refusals 1/100 98/100