mradermacher/aya-expanse-8b-ungated-GGUF
Same weights, converted vs adamo1139/aya-expanse-8b-ungated. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/96, Attention 0/128
Same weights, converted vs adamo1139/aya-expanse-8b-ungated. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/96, Attention 0/128