Saxo/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B
LoRA-style vs meta-llama/Llama-3.1-8B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 0/1
4 derivatives checked
- featherless-ai-quants/Saxo-Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B-GGUF: Quantization
- DevQuasar-12/Saxo.Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B-GGUF: Same weights, converted
- joongi007/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B-GGUF: Quantization
- bigdefence/llama-3.1-8b-dacon: LoRA-style