mradermacher/QalbunLLM-V1-GGUF
Same weights, converted vs Qalbun-AI/QalbunLLM-V1. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64
Same weights, converted vs Qalbun-AI/QalbunLLM-V1. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64