mradermacher/Xgen-9B-Merge-GGUF
Same weights, converted vs Disya/Xgen-9B-Merge. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/91, MLP 0/135, Attention 0/180
Same weights, converted vs Disya/Xgen-9B-Merge. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/91, MLP 0/135, Attention 0/180