LocalAI-io/privacy-filter-nemotron-GGUF
Same weights, converted vs OpenMed/privacy-filter-nemotron. Same weights stored in another dtype (BF16 → F16/F32), plus 58 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/17, MLP 0/16, Attention 0/64
Same weights, converted vs OpenMed/privacy-filter-nemotron. Same weights stored in another dtype (BF16 → F16/F32), plus 58 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/17, MLP 0/16, Attention 0/64