meta-llama/Llama-Guard-3-8B
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- legraphista/Llama-Guard-3-8B-IMat-GGUF: Same weights, converted
- mradermacher/Llama-Guard-3-8B-i1-GGUF: Quantization
- mradermacher/Llama-Guard-3-8B-GGUF: Same weights, converted
- eaddario/Llama-Guard-3-8B-GGUF: Same weights, converted
- featherless-ai-quants/meta-llama-Llama-Guard-3-8B-GGUF: Quantization
- DevQuasar-8/meta-llama.Llama-Guard-3-8B-GGUF: Same weights, converted
- MaziyarPanahi/Llama-Guard-3-8B-GGUF: Same weights, converted
- tensorblock/Llama-Guard-3-8B-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.