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