mlx-community/Skyfall-31B-v4.2-heretic-mlx-fp16
Same weights, converted vs coder3101/Skyfall-31B-v4.2-heretic. Same weights stored in another dtype (BF16 → F16).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/109, MLP 0/162, Attention 0/216
Same weights, converted vs coder3101/Skyfall-31B-v4.2-heretic. Same weights stored in another dtype (BF16 → F16).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/109, MLP 0/162, Attention 0/216