aniruddhabagal/fraud-sentinel-1b
Partial fine-tune vs mlx-community/Llama-3.2-1B-Instruct-4bit. Partial change: 39% of the weights changed (attention, mlp), in 8 of 16 layers.
Tensors changed: Embeddings 0/3, Norms 0/33, MLP 72/144, Attention 96/192
Partial fine-tune vs mlx-community/Llama-3.2-1B-Instruct-4bit. Partial change: 39% of the weights changed (attention, mlp), in 8 of 16 layers.
Tensors changed: Embeddings 0/3, Norms 0/33, MLP 72/144, Attention 96/192