OpenYourMind/OpenYourMind-Qwen3.6-35B-A3B-kuato-DPO-abliterated-uncensored
Partial fine-tune vs Qwen/Qwen3.6-35B-A3B. Partial change: 32% of the weights changed (attention, mlp), in 40 of 40 layers.
Tensors changed: Embeddings 0/5, Attention 70/392, MLP 160/399, Norms 0/247, lm_head 0/1, other 0/1