Comply2Reg/regulatory-alert-triage-qwen3-4b-v1

Partial fine-tune vs mlx-community/Qwen3-4B-Instruct-2507-4bit. Partial change: 40% of the weights changed (attention, mlp), in 16 of 36 layers.

Tensors changed: Embeddings 0/3, Norms 0/145, MLP 144/324, Attention 192/432

On the Hub · Downloads on Model Pulse