I have an idea to collect all open-source LLM models to launch one full-fledged service for working with models, that is, we will use one mini LLM model to recognize a task, write code, translate text, solve problems, etc., and then transfer the task to a model designed for this, We will use Petals to run models, we can make your own cryptocurrency and pay people who allocate their servers to run Petals to support models, what do you think of this idea?
There’s already a couple of startups working on similar things, check https://withmartian.com for example (not a reason not to do anything ofc). Interested in what it becomes!