nbeerbower/Lyra4-Gutenberg2-12B

nbeerbower/Lyra4-Gutenberg2-12B is a 12 billion parameter language model, fine-tuned from Sao10K/MN-12B-Lyra-v4, with an increased sequence length and a 32768 token context window. It was trained using ORPO on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo datasets, formatted with ChatML. This model is designed for general language tasks, leveraging its extended context and specific DPO fine-tuning.