Cohere-command-r-plus

Command R+ is a highly performant generative large language model, optimized for a variety of use cases including reasoning, summarization, and question answering. It is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety. The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. Command R+ has a context window up to 128k.