where's the technical details ?
where are the actual technical details of the model ?
how many (B)illion parameters (24B / 32B / 70B ...) ?
what is the base model ?
what architecture type model is it (Llama / Mistral / Gemma ... ) ?
number of layers ?
number of attention heads ?
can it use Instructions / tools ?
any quickstart code ?
usage guidelines for best results ?
even example would be a good start.
what embedding model is used ? how to count tokens ?
any performance comparison you want to share ?
...
beside context length - nothing is supplied
You're better off looking at the original model card for further details:
https://huggingface.co/CohereForAI/c4ai-command-a-03-2025
The details given here are meant to be just useful "at a glance" rather than a full deep dive into everything about the model, so you can quickly determine if it's something that interests you