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

Downloads last month
19
Safetensors
Model size
24B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Sabomako/Mistral-Small-3.2-24B-Instruct-2506-heretic