arianraje/qwen3-4b-mamba3-hybrid-stage2b-kd-bias0
Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 77/91, MLP 108/108, Attention 36/36
Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 77/91, MLP 108/108, Attention 36/36