Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MiniGPT-4

minigpt-4.github.io

Post reply on HN
Print view View original

71–80 of 337 posts

Re: MiniGPT-4

#71

Post by nashashmi »

collaborative wrote: post #25
Tepix wrote: post #12

I think it's poor form that they are taking the GPT-4 name for an unrelated project. After all, the underlying Vicuna is merely a fine-tuned LLaMA. Plus they use the smaller 13B version. The results look interesting, however. Here's hoping that they'll add GTPQ 4bit quantizing so the 65B version of the model can be run on 2x 3090.

Adding GPT4 to anything now increases marketing x4. So many AI news coming out lately that not adding it risks drowning in a sea of info.. even in the case of a good project

They can always say GPT-like. Or miniaturized GPT-like LLM.

Re: MiniGPT-4

#72

Post by sampa »

mewpmewp2 wrote: post #53
redox99 wrote: post #46

Earlier quoted context omitted.

It's pretty simple actually. Get a 3090 or 4090. Forget about AMD.

Should I get a gaming PC with 4090 if I want to get into personal side projects in ML and also games? Do I need dualboot? Or is Windows good?

you can run Windows in VM and passthrough your videocard to it. So it's basically a native gaming (3-5% cost) w/o reboots. Look for VFIO.

Re: MiniGPT-4

#73

Post by devinprater »

Holy crap! If this has image to text, and can run on a CPU, even with 16 GB RAM, one could hook up an NVDA addon, straight Python so it shouldn't be too hard, and have AI read whatever the user wants. Pictures, video frames, UI's, and if it can break the UI down into something the screen reader can understand, boom!

Re: MiniGPT-4

#74

Post by Gravityloss »

MattPalmer1086 wrote: post #63
guax wrote: post #48

Earlier quoted context omitted.

And just like webdev, each of those were done in a different platform and require arcane incantations and 5h of doc perusing to make it work on your system.

You can just ask GPT how to do it. Much like a lot of web dev!

at some point someone makes a service where you can let AI take over your computer directly. Easier that way! Curling straight to shell taken to next level.

Re: MiniGPT-4

#75

Post by wwalexander »

MrGilbert wrote: post #19
sho wrote: post #14

Earlier quoted context omitted.

> they're doing something really simple -- take BLIP2's ViT-L+Q-former, connect it to Vicuna-13B with a linear layer, and train just the tiny layer on some datasets of image-text pairs Oh yes. Simple! Jesus, this ML stuff makes a humble web dev like myself feel like a dog trying to read Tolstoy.

Just get rid of all the abbreviations in your mind - they seem to be very intimidating. I really liked the explanation that Stephen Wolfram did on ChatGPT: https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-... Maybe someone has resources to understand machine-learning on an ELI5 level.

Wow, he waits until halfway through the article to mention A New Kind of Science. Usually he works it into the first couple of paragraphs!

Re: MiniGPT-4

#76

Post by amelius »

mjburgess wrote: post #17
sho wrote: post #14

Earlier quoted context omitted.

> they're doing something really simple -- take BLIP2's ViT-L+Q-former, connect it to Vicuna-13B with a linear layer, and train just the tiny layer on some datasets of image-text pairs Oh yes. Simple! Jesus, this ML stuff makes a humble web dev like myself feel like a dog trying to read Tolstoy.

In practice, it's a lot more like web dev than you might imagine. The above means that the approach is web-dev like gluing, almost literally just, from existingliba import someop from existinglibb import anotherop from someaifw import glue a = someop(X) b = glue(a) Y = anotherop(b)

It's more like gardening:

    1. plant seed
    2. ...wait a very long time...
    3. observe completely unexpected but cool result
The unexpected part of step 3 is what makes this very different from any kind of engineering, even webdev.

Of course, there is a lot of engineering involved in good ML, but that is more comparable to agricultural engineering in the sense that it's just a lot of dumb plumbing that any engineer can do without knowledge of the actual application.

Re: MiniGPT-4

#77

Post by HarHarVeryFunny »

Uehreka wrote: post #61
collaborative wrote: post #25

Earlier quoted context omitted.

Adding GPT4 to anything now increases marketing x4. So many AI news coming out lately that not adding it risks drowning in a sea of info.. even in the case of a good project

The word for this is “trademark infringement”. You are specifically not allowed to capitalize on the marketing of another entity’s product to bolster yours by implying through your name that you are somehow related. This is why “DALL-E Mini” had to change their name to craiyon.

It's also just (deliberately) misleading. It's based on the 13B Vicuna/Llama model, not 175B GPT-3 or 1T GPT-4. There is zero justification for calling it MiniGPT-4.

A more honest name would be Visual-Vicuna or Son-of-BLIP.

Re: MiniGPT-4

#78

Post by teruakohatu »

mjburgess wrote: post #17
sho wrote: post #14

Earlier quoted context omitted.

> they're doing something really simple -- take BLIP2's ViT-L+Q-former, connect it to Vicuna-13B with a linear layer, and train just the tiny layer on some datasets of image-text pairs Oh yes. Simple! Jesus, this ML stuff makes a humble web dev like myself feel like a dog trying to read Tolstoy.

In practice, it's a lot more like web dev than you might imagine. The above means that the approach is web-dev like gluing, almost literally just, from existingliba import someop from existinglibb import anotherop from someaifw import glue a = someop(X) b = glue(a) Y = anotherop(b)

There is a little more to it than that. Abstractions in ML are very leaky.

Re: MiniGPT-4

#79

Post by 152334H »

jack_riminton wrote: post #67
152334H wrote: post #39

Earlier quoted context omitted.

I don't have much experience myself. I only started ~10 months ago -- just a month or two before Stable Diffusion. You just have to do it every day. It's fun!

Can you recommend what kind of small daily activities would help a web dev get into it?

Regardless of what you want to learn, "small daily activities" is a bit hard. You can learn some stuff by osmosis, following the feeds of AI devs && AI channels, but the bulk of what I learn comes from starting projects & digging into code & reading papers.

If you can hold attention span over several days (I can't), work on a project bit-by-bit. Just make sure it uses modern AI stuff, and that you have smart people to talk around with.

Re: MiniGPT-4

#80

Post by anonzzzies »

selfhoster11 wrote: post #38
sho wrote: post #14

Earlier quoted context omitted.

> they're doing something really simple -- take BLIP2's ViT-L+Q-former, connect it to Vicuna-13B with a linear layer, and train just the tiny layer on some datasets of image-text pairs Oh yes. Simple! Jesus, this ML stuff makes a humble web dev like myself feel like a dog trying to read Tolstoy.

Seriously, ChatGPT was the thing that gave me a foothold into the AI/machine learning world... because it gave me hope that a mere mortal can achieve something reasonable with this tech without a crazy amount of work and educational background.

There are really great resources now from eli5 about all of this tech to books like ‘the little learner’ which any programmer can get into. Yes, it takes effort but it is a great time for it.
Post reply on HN