DevQuasar/MBZUAI-Paris.Nile-Chat-12B-GGUF
Same weights, converted vs MBZUAI-Paris/Nile-Chat-12B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192
Same weights, converted vs MBZUAI-Paris/Nile-Chat-12B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192