donedynamics/Qwen3.8-27B-heretic-VL-MLX-bf16
Partial fine-tune vs trohrbaugh/Qwen3.8-27B-heretic-ara. Partial change: 0% of the weights changed (norms), in 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 161/209, Attention 0/400, MLP 0/192
Partial fine-tune vs trohrbaugh/Qwen3.8-27B-heretic-ara. Partial change: 0% of the weights changed (norms), in 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 161/209, Attention 0/400, MLP 0/192