In this chapter, we'll give you an overview of the new Command model for generation, and its uses.
Command is Cohere’s flagship text generation model. It is trained to follow user commands and to be instantly useful in practical business applications.
Command ranks at the top of the HELM benchmark, an evaluation leaderboard comparing large language models on a wide number of tasks (March ‘23 results). HELM is the Holistic Evaluation of Language Models from Stanford University.
1- Continuously improving
Future-proof your language model technology by relying on a model that keeps improving over time. Join the Discord to keep learning about the latest releases.
2- Trained on practical use cases
We especially train Command on data that aids reliable business applications, like summarization, copywriting, extraction, and question answering.
3- Optimized for business priorities
Command can instantly perform many tasks by default. But if you need to incorporate company-specific language or more advanced use cases, then Command can be customized to hyperfocus on your use case.
Ask Command multiple questions about a document in order to assign a category to the document, extract a piece of information, or answer a general question about the document.
Where answering a few questions about a document can save you a few minutes, doing it for thousands of documents can save a company years.
Integrating Command into your products unlocks a world of possibilities. Dedicate your time to product innovation, while Cohere handles model improvement and deployment for you.
Updated about 1 month ago
That's it! Now you know how to prompt and train generative models with the Generate endpoint!