Update llama-run to include temperature option

[ericcurtin]

This commit updates the examples/run/README.md file to include a new option for setting the temperature and updates the run.cpp file to parse this option.

[ngxson]

Tbh I'm not sure what's the long-term plan for llama-run.

My thought is that if now we add --temp, I'm pretty sure someone will also add other sampling params like top-k, top-p, DRY, etc in the near future, to a point that it will defeat the initial goal of llama-run which is "just run".

[ericcurtin]

Tbh I'm not sure what's the long-term plan for llama-run.

My thought is that if now we add --temp, I'm pretty sure someone will also add other sampling params like top-k, top-p, DRY, etc in the near future, to a point that it will defeat the initial goal of llama-run which is "just run".

I had a use case for --temp.

If somebody has a use case for extra arguments, I don't have an immediate issue with merging them. Yes, I'd hope it would be less complex than llama-cli, but personally I have no issue with people adding extra args if they need them.

[ericcurtin]

But of course, simple use cases like:

llama-run smollm:135m

should continue to work.

[ericcurtin]

This should be an easy review @slaren @ggerganov