mradermacher/Qwen3-4B-Base-Ar-Extended-GGUF
Same weights, converted vs Mohaddz/Qwen3-4B-Base-Ar-Extended. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144
Same weights, converted vs Mohaddz/Qwen3-4B-Base-Ar-Extended. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144