FedericoFB/NemotronLabs-AI-for-Media-Sports-Tennis-GGUF-BF16
Same weights, converted vs nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Tennis. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 92 new tensors.
Tensors changed: Norms 0/53, Embeddings 0/1, lm_head 0/1