openaccess-ai-collective

/

wizard-mega-13b

like 105

You give two examples of the following prompt format:
### Instruction: <question>\n\n### Assistant: <answer>\n\n

But your hugging face space uses this version of the Alpaca prompt format:
### Instruction: \n<question>\n\n### Response:\n<answer>\n\n

And this version of the Vicuna 1.1 prompt format:
USER: <question>\nASSISTANT: <answer>\n

But reading the axolotl source code and looking at your config file, shows that you trained two of the models with a different version of the Vicuna 1.1 instruction format, and one of the models with the Alpaca instruction format. Which is a weird way of doing it.

Two of the datasets:
USER: <question> ASSISTANT: <answer></s>

The other dataset:
Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n<question>\n\n### Response:\n<answer>

So what format should I actually use?

EDIT: fixed my mistake about the hugging face space