Running a 180B parameter LLM on a single Apple M2 Ultra

Re:Running a 180B parameter LLM on a single Apple M2 Ultra by passion__desire on Thursday September 07, 2023 @01:53PM (#37422875)

Meta doesn't interact with its users in very obvious ways which MS, Google do. All its models magic happen behind the scenes. Meta can continue to release 2nd best models to undercut others and them going far too ahead. And Open Source community will take it from there. Dall-E is dead.

[ Parent | on HN ]

Re:Running a 180B parameter LLM on a single Apple M2 Ultra by bugglebeetle on Thursday September 07, 2023 @02:04PM (#37423063)

And if all open source extends their models, they can accrue those benefits back to themselves. This is already how they’ve become such a huge player in machine learning (open sourcing amazing stuff).

[ Parent | on HN ]

Re:Running a 180B parameter LLM on a single Apple M2 Ultra by astrange on Thursday September 07, 2023 @07:27PM (#37427098)

I think Dall-E isn't actually dead, but was merely renamed Bing Image Creator.

[ Parent | on HN ]