Artples/L-MChat-Small

Artples/L-MChat-Small is a 3 billion parameter language model created by Artples, developed through a SLERP merge of rhysjones/phi-2-orange-v2 and Weyaxi/Einstein-v4-phi2. This model explores the performance of smaller merged architectures, offering a compact solution with a 2048-token context length. It is designed for general chat applications and demonstrates competitive performance on various benchmarks, including an average score of 63.14 on the Open LLM Leaderboard.