Hello,
I’ve found that in the go_cli.py code, the prompt is sent to https://cli.gorilla-llm.com, which returns the corresponding commands. Since the model for Gorilla is public, and there are instructions for local inference available here, I believe it would be great to be able to learn about the code that powers https://cli.gorilla-llm.com/commands_v2.
This would allow us to build and run a version of Gorilla-CLI from a local server, offering more flexibility and control, especially for those who prefer or need a self-hosted solution.
Hello,
I’ve found that in the
go_cli.pycode, the prompt is sent to https://cli.gorilla-llm.com, which returns the corresponding commands. Since the model for Gorilla is public, and there are instructions for local inference available here, I believe it would be great to be able to learn about the code that powers https://cli.gorilla-llm.com/commands_v2.This would allow us to build and run a version of Gorilla-CLI from a local server, offering more flexibility and control, especially for those who prefer or need a self-hosted solution.