DavidAU/Qwen3.5-13B-Deckard-Heretic-Uncensored-Thinking
Partial fine-tune vs trohrbaugh/Qwen3.5-9B-heretic-v2. Partial change: 69% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 65/215, Attention 161/332, MLP 96/208