Roll out your own ChatGPT

Re:Roll out your own ChatGPT by itworkslikethat on Monday December 26, 2022 @05:07AM (#34136312)

I tried them all, and continue trying when new things come out. No open model is capable of even remotely approaching the capabilities of GPT-3 or ChatGPT. Even if you had an equivalent trained model, running it would require enormous hardware.

While Stable Diffusion is pretty comparable to DALL-E 2 even on small hardware (such as M1 MacBook Air), this doesn't hold true for large language models. These need much, much more VRAM.

[ Parent | on HN ]

Re:Roll out your own ChatGPT by ilaksh on Monday December 26, 2022 @10:25AM (#34138298)

text-davinci-003 is extremely close, or code-davinci-002

[ Parent | on HN ]

Re:Roll out your own ChatGPT by v3ss0n on Monday December 26, 2022 @12:04PM (#34139475)

None of that model available to run on your hardware

[ Parent | on HN ]

Re:Roll out your own ChatGPT by supermatt on Tuesday December 27, 2022 @03:31PM (#34153379)

thats a real shame. Any idea why GPT-3 generations differ so much? Maybe eleuther/whatever could look at refining their model in a similar way.

[ Parent | on HN ]

Re:Roll out your own ChatGPT by itworkslikethat on Thursday December 29, 2022 @03:04PM (#34177228)

It's most likely because of the actual runtime size of the model. All the open models are sized for consumer-grade devices, and thus 10x-100x smaller than whatever OpenAI runs (probably around 100+ GB in VRAM, maybe even some multiples more). This is one of the main reasons why their API makes business sense - it's not practical at all to run models like GPT-3 yourself, and training them costs incredible amount of money too.

[ Parent | on HN ]