adpena/Vertigo-Qwen3.5-4B-v0.5-4bit
Partial fine-tune vs mlx-community/Qwen3.5-4B-4bit. Partial change: 21% of the weights changed (attention, mlp), in 8 of 32 layers.
Tensors changed: Embeddings 0/3, Norms 0/105, Attention 114/528, MLP 72/288
Partial fine-tune vs mlx-community/Qwen3.5-4B-4bit. Partial change: 21% of the weights changed (attention, mlp), in 8 of 32 layers.
Tensors changed: Embeddings 0/3, Norms 0/105, Attention 114/528, MLP 72/288