mradermacher/Luna-7B-A4B-GGUF
Same weights, converted vs beyoru/Luna-7B-A4B. Same weights stored in another dtype (F32 → F16/F32), plus 108 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/36, Attention 0/144
Same weights, converted vs beyoru/Luna-7B-A4B. Same weights stored in another dtype (F32 → F16/F32), plus 108 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/36, Attention 0/144