mradermacher/Lythri-7B-A4B-GGUF
Same weights, converted vs Lythri/Lythri-7B-A4B. Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.
Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132
Same weights, converted vs Lythri/Lythri-7B-A4B. Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.
Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132