jupyter-agent/jupyter-agent-qwen3-4b-instruct

Full fine-tune vs Qwen/Qwen3-4B-Instruct-2507. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 127/145, MLP 108/108, Attention 144/144

1 derivatives checked