This model is in active development. Our team is pushing hard to ensure command is safe, and helpful for our users. As you experiment with the model and run into issues, please help us by flagging it to our team by emailing us at [email protected].
Command is Cohere's generative model that responds well with instruction-like prompts, and it's available in two sizes:
command model demonstrates better performance, and
command-light is a great option for developers who require fast response, like those building chatbots.
To reduce the turnaround time for releases, we have nightly versions of command available. This means that every week, you can expect the performance of
command-nightly-* to improve.
If you were previously using the
command-xlarge-20221108model, you will now be redirected to the
command-nightlymodel. Please note that access to the
command-xlarge-20221108model will be discontinued after January 30, 2023. The
command-nightlymodel has shown enhancements in all generative tasks, and we anticipate you will notice an improvement.
Install the SDK, if you haven't already.
pip install cohere
Then, set up the Cohere client.
import cohere co = cohere.Client(api_key)
prompt = "Write an introductory paragraph for a blog post about language models."
response = co.generate( model='command-nightly', prompt = prompt, max_tokens=200, # This parameter is optional. temperature=0.750) intro_paragraph = response.generations.text
Can users train Command?
Users cannot train Command in OS at this time. However, our team can handle this on a case by case basis. Please email [email protected] if you’re interested in training this model.
Where can I leave feedback about Cohere's generative models?
Please leave feedback in #product-updates on Discord.
Updated about 1 month ago