werty1248/Llama-3-Ko-8B-OpenOrca
Full fine-tune vs beomi/Llama-3-Open-Ko-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/Llama-3-Ko-8B-OpenOrca-i1-GGUF: Quantization
- featherless-ai-quants/werty1248-Llama-3-Ko-8B-OpenOrca-GGUF: Quantization
- mradermacher/Llama-3-Ko-8B-OpenOrca-GGUF: Same weights, converted