this post was submitted on 26 Jul 2023
3 points (71.4% liked)

LocalLLaMA

3002 readers
23 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

founded 2 years ago
MODERATORS
SkySyrup@sh.itjust.works
pax@sh.itjust.works
noneabove1182@sh.itjust.works
Smokeydope@lemmy.world
MonsterBug@sh.itjust.works
3
What determines the format of the prompt template? (lemmy.world)
submitted 2 years ago by fhein@lemmy.world to c/localllama@sh.itjust.works
4 comments fedilink hide all child comments
 

I'm trying to learn more about LLMs, but I haven't found any explanation for what determines which prompt template format a model requires.

For example meta-llama's llama-2 requires this format:

...INST and <> tags, BOS and EOS tokens...

But if I instead download's TheBloke's version of llama-2 the prompt template should instead be:

SYSTEM: ...

USER: {prompt}

ASSISTANT:

I thought this would have been determined how the original training data was formatted, but afaik TheBloke only converted the llama-2 models from one format to another. Looking at the documentation for the GGML format I don't see anything related to the prompt being embedded in the model file.

Anyone who understands this stuff who could point me in the right direction?

you are viewing a single comment's thread
view the rest of the comments
[โ€“] rufus@discuss.tchncs.de 2 points 2 years ago (1 children)

That's probably the most reasonable thing you can do.

I'm not sure how much of a difference we expect from 100% the correct prompt compared to something roughly in that direction. I've been tinkering around with instruction style tuned models (from the previous/first llama) and sometimes it doesn't seem to matter. I also sometimes used a 'wrong' prompt for days and couldn't tell. Maybe the models are 'intelligent' enough to compensate for that. I'm not sure. I usually try to get it right to get all the performance out of it.