Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B. Parent comment
But you should be able to get it to do stuff just by telling it what you want. Note that it's completion tuned (not chat-tuned), so it should perform better on single-turn conversations.
There are no comments on this comment yet.
But you should be able to get it to do stuff just by telling it what you want. Note that it's completion tuned (not chat-tuned), so it should perform better on single-turn conversations.