DevQuasar/nvidia.Nemotron-Terminal-8B-GGUF
Same weights, converted vs nvidia/Nemotron-Terminal-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1, Embeddings 0/1
Same weights, converted vs nvidia/Nemotron-Terminal-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1, Embeddings 0/1