News for hackers. Stuff that matters.

A comment on Releasing Persimmon-8B. Parent comment

Re:Releasing Persimmon-8B by sbierwagen on Thursday September 07, 2023 @04:17PM (#37424968)
phi-1 supposedly does 50.6 on HumanEval with 1.3B parameters. (Python only) https://arxiv.org/abs/2306.11644

Weights haven't been released, though.

[ Parent | on HN ]
Re:Releasing Persimmon-8B by imjonse on Thursday September 07, 2023 @04:35PM (#37425195)
no code or dataset either for phi-1.
[ Parent | on HN ]
Re:Releasing Persimmon-8B by euclaise on Friday September 08, 2023 @08:28AM (#37432654)
phi-1 is a code-specific base model, with further finetuning on top of that. This is a general language base model, not really comparable.
[ Parent | on HN ]