I've tested this approach on a single-language (English) LlaMA, and it worked great, except:
it didn't get the LinkedIn layoff answer right
it didn't output any spaces between words
But the thing that I wonder about is real-life use: when you address a question to an LLM, you don't normally provide the context as well.
Is there a way to provide it anyway?
Also, is there any specific finetuning procedure that'd make the model better at using this approach?
I've tested this approach on a single-language (English) LlaMA, and it worked great, except:
But the thing that I wonder about is real-life use: when you address a question to an LLM, you don't normally provide the context as well. Is there a way to provide it anyway? Also, is there any specific finetuning procedure that'd make the model better at using this approach?