Jasaxion/MathSmith-HC-Qwen3-14B-ShortCoT

Full fine-tune vs Qwen/Qwen3-14B. Fine-tune: 95% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 146/161, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked