Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Can you give an example on how you prompted the model? Your issue is probably related to that, but I would need an example to be sure. I've found the 7b Alpaca model [1] to work surprisingly well! Here's how you're supposed to prompt it:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction: {instruction}

### Response:

or

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction: {instruction}

### Input: {input}

### Response:

[1] https://github.com/cocktailpeanut/dalai



Barebones llama is just a text completion model. You can give it a prompt like

    A conversation between a human and assistant

    Human: How old is the sun?
    Assistant:
And it will complete it.

Alpaca/Dalai are finetuned on a dataset that's formatted as this:

    ### Instruction: {instruction}

    ### Input: {input}

    ### Response:
So even without pre-prompting in this format it's going to be heavily biased towards performing completions in this format anyways.

It's always helpful to finetune on a preformatted prompt depending on what your task is.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: