Dupe https://news.ycombinator.com/item?id=27727009
Is it a dupe though if it's a blog post, as opposed to the earlier Github submission?
GPT-J: GPT-3 Democratized
11–20 of 41 posts
Re: GPT-J: GPT-3 Democratized
#12I run GPT-J on a Titan RTX where I am writing a novel with it. To make it generate about 20k tokens or two pages of content takes a few minutes . I would say the output is comparable to other language models quality and so forth. Note that refinement or transfer learning doesn’t apply anymore it’s more like using a zero shot classifier or in other words you have to craft the input like Siri or wolfram alpha but expec…
Could you say more?
Re: GPT-J: GPT-3 Democratized
#13Re: GPT-J: GPT-3 Democratized
#14Re: GPT-J: GPT-3 Democratized
#15Earlier quoted context omitted.
There is open and there is open . OpenAI is more like the latter, similar to OpenVMS. EDIT: Or OpenWindows desktop environment.
So not really open, and just bullshit marketing.
Re: GPT-J: GPT-3 Democratized
#16I run GPT-J on a Titan RTX where I am writing a novel with it. To make it generate about 20k tokens or two pages of content takes a few minutes . I would say the output is comparable to other language models quality and so forth. Note that refinement or transfer learning doesn’t apply anymore it’s more like using a zero shot classifier or in other words you have to craft the input like Siri or wolfram alpha but expec…
Re: GPT-J: GPT-3 Democratized
#17Re: GPT-J: GPT-3 Democratized
#18I run GPT-J on a Titan RTX where I am writing a novel with it. To make it generate about 20k tokens or two pages of content takes a few minutes . I would say the output is comparable to other language models quality and so forth. Note that refinement or transfer learning doesn’t apply anymore it’s more like using a zero shot classifier or in other words you have to craft the input like Siri or wolfram alpha but expec…
I've primarily been using GPT-3 (and burning through millions of tokens) so I've been experimenting with GPT-J more lately and I've found it makes significantly more basic logic errors (e.g. mixing up pronouns, "forgetting" characters, using new characters), which makes me lean more towards constantly regenerating text versus revising it, and I feel like I'm backed into a box of having to babysit ~100-200 tokens at a time instead of generating significantly more at a time like I do with GPT-3.
I also built a quick tool that lets me adjust how much context I'm using in the prompt and generate 2-3 side-by-side completions to pick and choose from (just to speed up the flow of `click best suggestion` --> `keep generating from there`), but I haven't integrated GPT-J yet since it just feels... lower quality (it feels similar to ~Babbage, IMO).
But being comparatively* free, I'm still excited about GPT-J. Do you have any tips or processes you've found to make it spit out higher-quality text? 20k tokens at a time is quite a lot -- do you also have problems with winding paths / staying on a general "plot"?
Would love to hear any suggestions you have, because I'd sure love to move off GPT-3 to something comparable in quality!
Re: GPT-J: GPT-3 Democratized
#19Re: GPT-J: GPT-3 Democratized
#20For every valid case, I see others that make my head hurt. Is it just a buzzword for telling a story with emotional appeal to users and investors?
Making something available to someone who didn’t have it earlier isn’t democratizing. And ignoring future considerations is just lazy.
If guns were invented today they’d probably touted as democratizing violence.