bunnycore/DeepQwen-3B-LCoT-SCE-R1

Partial fine-tune vs bunnycore/DeepQwen-3B-LCoT-SCE. Partial change: 90% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 3/73, MLP 108/108, Attention 145/252

1 derivatives checked