Aqua00/Nemotron-3-Embed-8B-GGUF
Same weights, converted vs nvidia/Nemotron-3-Embed-8B-BF16. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Norms 0/69, MLP 0/102, Attention 0/136, Embeddings 0/1
Same weights, converted vs nvidia/Nemotron-3-Embed-8B-BF16. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Norms 0/69, MLP 0/102, Attention 0/136, Embeddings 0/1