groxaxo/GeeniQwos-14b
Partial fine-tune vs mlx-community/Qwen3-14B-4bit. Partial change: 9% of the weights changed (attention, mlp), in 4 of 40 layers.
Tensors changed: Embeddings 0/3, Norms 0/161, MLP 36/360, Attention 48/480, lm_head 0/3
Partial fine-tune vs mlx-community/Qwen3-14B-4bit. Partial change: 9% of the weights changed (attention, mlp), in 4 of 40 layers.
Tensors changed: Embeddings 0/3, Norms 0/161, MLP 36/360, Attention 48/480, lm_head 0/3