Modelpublic

meangrinch/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill-heretic-v3

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

2likes19downloads

Model Card

Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill-heretic-v3

Abliterated (uncensored) weights generated with an unreleased version of Heretic using the experimental Arbitrary-Rank Ablation (ARA) method.

See https://github.com/p-e-w/heretic/pull/211 for details about ARA.

Parameter	Value
start_layer_index	16
end_layer_index	25
preserve_good_behavior_weight	0.5606
steer_bad_behavior_weight	0.0002
overcorrect_relative_weight	0.8662
neighbor_count	15

Metric	Value
Refusals	4/100
KL divergence	0.0079

A lower refusal count means the model is more willing to engage with restricted prompts.

A lower KL divergence means the abliterated weights deviate less from the original model's distribution (i.e. less capability degradation).