Hacker News Reader

I'm a newbie to this stuff, but I did manage to get Dalai Llama up and running with llama and alpaca 7B and 13B.

The results I get seem to be random spitouts of reddit or facebook posts. Very often it even says something like "Next Post >>" or has a timestamp of the post.

Is this using the same model? Is there some kind of tuning I have to do?

View on HN

You have to prompt with the format Stanford tuned it on:

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:

Reply on news.ycombinator.com