The Yi model family, created by a team of authors including Alex Young and Shawn Yue, features language and multimodal models with impressive capabilities. These models are built on pretrained language models and expanded to include chat models, long context models, depth-upscaled models, and vision-language models. The models have shown strong performance on various benchmarks like MMLU, with chat models receiving high human preference rates on platforms like AlpacaEval and Chatbot Arena. The team credits the success of the Yi models to high-quality data obtained through extensive data engineering efforts. By continually refining their models and scaling up parameters, they aim to create even more powerful frontier models.
https://arxiv.org/abs/2403.04652