vandijklab/C2S-Scale-Gemma-2-27B

C2S-Scale-Gemma-2-27B is a 27 billion parameter language model developed by van Dijk Lab (Yale), Google Research, and Google DeepMind, built upon the Gemma-2 architecture. Fine-tuned for single-cell biology, it processes scRNA-seq data as 'cell sentences' to understand gene expression. This model excels at tasks like cell type prediction, tissue classification, and generating gene expression profiles, trained on over 57 million cells with a 32768 token context length.