mradermacher/Aira-2-774M-GGUF
Same weights, converted vs nicholasKluge/Aira-2-774M. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/72, Norms 0/146, MLP 0/72, Embeddings 0/2
Same weights, converted vs nicholasKluge/Aira-2-774M. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/72, Norms 0/146, MLP 0/72, Embeddings 0/2