mradermacher/zira-researcher-GGUF
Same weights, converted vs 0xvoid0000/zira-researcher. Same weights stored in another dtype (F16 → F16/F32), plus 24 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32
Same weights, converted vs 0xvoid0000/zira-researcher. Same weights stored in another dtype (F16 → F16/F32), plus 24 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32