mradermacher/Nile-Chat-4B-GGUF
Same weights, converted vs MBZUAI-Paris/Nile-Chat-4B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136
Same weights, converted vs MBZUAI-Paris/Nile-Chat-4B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136