gabriellarson/UIGEN-X-32B-0727-GGUF
Same weights, converted vs Tesslate/UIGEN-X-32B-0727. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/192, Attention 0/256, lm_head 0/1
Same weights, converted vs Tesslate/UIGEN-X-32B-0727. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/192, Attention 0/256, lm_head 0/1