elinas/Llama-3-15B-Instruct-ft-v2

elinas/Llama-3-15B-Instruct-ft-v2 is a 15 billion parameter instruction-tuned language model, a QLoRA finetune based on a passthrough merge of Llama-3-15B-Instruct-zeroed. It was finetuned with an 8192 token context length, targeting all LoRA modules for enhanced training. This model is primarily an experimental finetune aimed at stabilizing performance after a complex merge, with future versions focusing on writing, logic, and coherency.