iknow-lab/llama-3.2-3B-wildguard-ko-2410
Full fine-tune vs Bllossom/llama-3.2-Korean-Bllossom-3B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112
1 derivatives checked
- mradermacher/llama-3.2-3B-wildguard-ko-2410-GGUF: Same weights, converted