DevQuasar-8/meta-llama.Meta-Llama-Guard-2-8B-GGUF
Same weights, converted vs meta-llama/Meta-Llama-Guard-2-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1
Same weights, converted vs meta-llama/Meta-Llama-Guard-2-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1