nanoandrew4/Nemotron-3-Embed-1B-GGUF
Same weights, converted vs nvidia/Nemotron-3-Embed-1B-BF16. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64
Same weights, converted vs nvidia/Nemotron-3-Embed-1B-BF16. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64