LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Is it just me or is prompt engineering basically useless with smaller models? (alien.top)

submitted 11 months ago by Weird_Foundation5044@alien.top to c/localllama@poweruser.forum

19 comments fedilink hide all child comments

I tried to apply a lot of prompting techniques in 7b and 13b models. And no matter how hard I tried, there was barely any improvement.

you are viewing a single comment's thread
view the rest of the comments

[–] phree_radical@alien.top 1 points 11 months ago

What you're referring to as "prompt engineering" is more accurately described as how to get good interpolations between ChatGPT behaviors. Those are specific instructions and behaviors that OpenAI trains their models on, in careful proportion designed to reach good generalization on them

And it's not that the models are too small -- Mistral 13b will be better than gpt-3.5-turbo. It's all about the training

Anyways that's why I try to loudly proclaim the benefits of few-shot examples and completion instead of instruction, until we have models trained the way OpenAI's are. If you're willing to write examples and dodge the chatbot trained behaviors, you can pretty much perform any task without need for training