abacusai/Slerp-CM-mist-dpo

abacusai/Slerp-CM-mist-dpo is a 7 billion parameter language model created by abacusai, formed by a Slerp Merge of cookinai/CatMacaroni-Slerp and mncai/mistral-7b-dpo-v5. This model features an 8192-token context length and demonstrates improved performance in TruthfulQA and GSM8K benchmarks compared to its base models. It is designed for general language understanding and generation tasks, aiming for a balanced performance across various academic benchmarks.