mradermacher/Llama-3.2-3B-NuminaQA-GGUF
Same weights, converted vs lkevinzc/Llama-3.2-3B-NuminaQA. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112
Same weights, converted vs lkevinzc/Llama-3.2-3B-NuminaQA. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112