Training LLM using local application

Hi guys,
as a AI newbie I’m looking to teach a LLM the way to use a local tool ; do i have to give the user manual to the LLM, to give the differrents possible actions, use tensorflow or pytorch?

Thanks for any help about the framework and AI tools to be used :slight_smile:

What is the local tool? What would the LLM prompts look like? What would you expect it to generate?

One could fine-tune LLMs for so-called tool use. See the docs regarding how to do this with TRL: Learning Tools (Experimental 🧪). It teaches an LLM how to use a calculator.

Note: this is pretty experimental.