mradermacher/sifr-0.8b-v3-GGUF
Same weights, converted vs mohamedlotfy50/sifr-0.8b-v3. Same weights stored in another dtype (BF16 → F16/F32), plus 18 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24
Same weights, converted vs mohamedlotfy50/sifr-0.8b-v3. Same weights stored in another dtype (BF16 → F16/F32), plus 18 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24