Text Generation
Transformers
Safetensors
English
stablelm
causal-lm
conversational
Eval Results
Inference Endpoints

recommended prompt structure

#12
by rozek - opened

Hello,

I've been experimenting with "stablelm-zephyr-3b" for quite a while now - with mediocre results until I (accidentally) formatted my prompt without the recommended <|endoftext|> - and suddenly, I got exciting results!

Hence my question: is the prompt example shown in the model card really correct?

Hi, will you please share your input prompt format. I am also trying out various prompt styles to get a better result for a common input prompt. It would be helpful to know yours :)

Sure, here is what I am using right now (based on the example from the model card):

<|user|>
List 3 synonyms for the word "tiny"
<|assistant|>
1. Dwarf
2. Little
3. Petite

Thus, simply omit the <|endoftext|>, that's it!

This is a good question. I would like to know as well.

Me too :)

Sign up or log in to comment