MK4-Research/LOREA-cyber-v5.8
Partial fine-tune vs mlx-community/Qwen3.6-35B-A3B-4bit. Partial change: 0% of the weights changed (attention), in 3 of 40 layers.
Tensors changed: Embeddings 0/3, Norms 0/131, Attention 36/660, MLP 0/960, lm_head 0/3
Partial fine-tune vs mlx-community/Qwen3.6-35B-A3B-4bit. Partial change: 0% of the weights changed (attention), in 3 of 40 layers.
Tensors changed: Embeddings 0/3, Norms 0/131, Attention 36/660, MLP 0/960, lm_head 0/3