It’s fine. They have a lot of cluster everything. You can try it.

Prompt inference?

They don’t return the likelihood.

Actually, they can return the likelihood? because they are generating model inside. They have a probability. They are sub-max distribution.

They just not return the likelihood.

I think if we can change the llama output layer, maybe we can get logs.

So label this cluster. Also use some kind of prompt to do a summary, right? Something like that.

If you only want to summarize, then that will give a very brief summary.

Oh, cool. You need to compare both.

One video would have all the data. It just says Nokia?

So we need to build a self-hosted one, how to talk to the city?

And we also have a local host LLM model. Yeah, LLM and Python.

It’s okay, because my LLM model has an open stack.

I choose the open AI interface stack right now.

All different.