VertexAIco/Bonsai-27b-MLX-Fast
Same weights, repacked vs prism-ml/Bonsai-27B-mlx-1bit. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: lm_head 0/3, Embeddings 0/6, Attention 0/984, MLP 0/598, Norms 0/289
Same weights, repacked vs prism-ml/Bonsai-27B-mlx-1bit. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: lm_head 0/3, Embeddings 0/6, Attention 0/984, MLP 0/598, Norms 0/289