News for hackers. Stuff that matters.

A comment on Show HN: Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B. Parent comment

Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by JoelJacobson on Saturday August 26, 2023 @08:48AM (#37272388)
That's what I've been using but still get that error.
[ Parent | on HN ]
Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by tomduncalf on Saturday August 26, 2023 @11:51AM (#37273925)
Same here, would be interested to know if there's a solution!

I created an issue, if you have an example prompt to add that would be helpful! https://github.com/jmorganca/ollama/issues/422

[ Parent | on HN ]
Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by jmorgan on Saturday August 26, 2023 @02:25PM (#37275483)
Thanks for creating an issue! And sorry for the error folks… working on it!
[ Parent | on HN ]
Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by tomduncalf on Sunday August 27, 2023 @03:50AM (#37280375)
Haha no need to apologise! Thanks for an amazing project :)
[ Parent | on HN ]
Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by pmarreck on Saturday August 26, 2023 @01:55PM (#37275161)
Datapoint here on an M1Max Macbook Pro: I use the triple doublequotes and I'm not getting that error
[ Parent | on HN ]