mradermacher/Lumina-Soft-1.2b-GGUF
Same weights, converted vs Umranz/Lumina-Soft-1.2b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24
Same weights, converted vs Umranz/Lumina-Soft-1.2b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24