mradermacher/Loxa-1.6B-GGUF
Same weights, converted vs frameai/Loxa-1.6B. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/47, MLP 0/69, Attention 0/92
Same weights, converted vs frameai/Loxa-1.6B. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/47, MLP 0/69, Attention 0/92