tsfrm/cheese-3b
Partial fine-tune vs mlx-community/Llama-3.2-3B-Instruct-4bit. Partial change: 50% of the weights changed (attention, mlp), in 16 of 28 layers.
Tensors changed: Embeddings 0/3, Norms 0/57, MLP 144/252, Attention 192/336
Partial fine-tune vs mlx-community/Llama-3.2-3B-Instruct-4bit. Partial change: 50% of the weights changed (attention, mlp), in 16 of 28 layers.
Tensors changed: Embeddings 0/3, Norms 0/57, MLP 144/252, Attention 192/336