mradermacher/Loxa-4B-GGUF
Same weights, converted vs frameai/Loxa-4B. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/144
Same weights, converted vs frameai/Loxa-4B. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/144