mradermacher/MMaDA-8B-Base-GGUF
Same weights, converted vs Gen-Verse/MMaDA-8B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/65, Attention 0/128, other 0/65, MLP 0/32, Embeddings 0/1
Same weights, converted vs Gen-Verse/MMaDA-8B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/65, Attention 0/128, other 0/65, MLP 0/32, Embeddings 0/1