Davd-b01/BigBang-Aquila-35B-Merged

Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 99% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/4, Attention 256/388, MLP 280/392, Norms 101/241, lm_head 1/1

3 derivatives checked