Modelpublic

catplusplus/Qwen3-VL-30B-A3B-Thinking-Heretic

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

1likes16downloads

Model Card

This model has been processed with heretic 1.1.0 to reduce refusals. It can generate text not suitable for all audiences

I used --orthogonalize-direction --row-normalization FULL --full-normalization-lora-rank 5

heretic only found attention layers but this appears enough to have arbitary conversations with AI safety lectures in practice. Anecdotally model seems to think better generally.

Parameters:

—direction_index = 28.60
—attn.oproj.maxweight = 1.46
—attn.oproj.maxweight_position = 32.05
—attn.oproj.minweight = 1.44
—attn.oproj.minweight_distance = 28.03

» [Trial 476] Refusals: 18/100, KL divergence: 0.0084