trohrbaugh/BigBang-v1-heretic

Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 96% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/5, Attention 261/392, MLP 280/399, Norms 100/247, lm_head 1/1, other 0/1

2 derivatives checked