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

Show HN: I fine-tuned Flan-T5. Can it cook?

abuqader.substack.com

Post reply on HN
Print view View original

21–30 of 45 posts

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#21

Post by cactusplant7374 »

spion wrote: post #11

For some reason, I find it really grating how most deep learning stuff are pretty much impossible to do without paying quite a bit to a 3rd party service by the hour. Its one of the rare things in computing that you can't get started with unless you have some significant resources - most other things you can theoretically do with any old laptop and internet connection (ok - you may need to pay once you get users, but…

Runpod and Colab are the easiest to get started. Google cloud has a crazy sales funnel that will make you go crazy.

$20 should get you pretty far I would think.

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#22

Post by cactusplant7374 »

Thinking out loud here: Generating recipes for novel, yet to be discovered dishes, sounds really exciting — like that time I added peanut butter to warm rice.

It would need a deep understanding of human brain chemistry to mix and match different flavors.

BTW, tried peanut butter rice with “le chef” and the recipe didn’t contain any liquid.

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#23

Post by askiiart »

vorpalhex wrote: post #13
spion wrote: post #11

For some reason, I find it really grating how most deep learning stuff are pretty much impossible to do without paying quite a bit to a 3rd party service by the hour. Its one of the rare things in computing that you can't get started with unless you have some significant resources - most other things you can theoretically do with any old laptop and internet connection (ok - you may need to pay once you get users, but…

You can get a lot of success by buying used gpus of the right sort (usually pro gpus, not gaming cards). There is still cost in terms of power - gpus run hot and loud.

I bought a Tesla K80 for ~$200 off eBay, and now it's going for less than $150, and you can essentially get the same but just 1 GPU for $100. It has 12 GB of VRAM, and works great for "medium-duty" machine learning and AIs like Stable Diffusion.

It does run hot (150W per GPU), and I've had to make a [custom solution to cool it](https://github.com/askiiart/k80-linux-cooling), but it works great considering the price.

By the way, you can essentially never have an application use the 2 GPUs in parallel in any useful way; I'd suggest just getting a K20X instead.

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#24

Post by p1necone »

rovr138 wrote: post #6
1024core wrote: post #4

OP does not mention that he's employed by BaseTen, the company behind "Blueprint" (which is mentioned repeatedly in the blog post). I noticed the repeated mentions and did some digging to find this out. Not cool, OP, not cool. See: https://www.baseten.co/blog/deploying-stable-diffusion

Not sure if it was added since, but 7 mins after, it has this, > Quick thanks to Baseten, where I work. As an employee, I had early access to Blueprint where I used their fine-tuning APIs and serverless GPUs, which made this process much faster. You can sign up for the waitlist at: blueprint.baseten.co

Wow, even the disclosure sounds like an ad.

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#25

Post by pascalr555 »

dools wrote: post #9

Sort of minor note but when I cook, I want the directions to contain the quantities. Rather than “heat oil in pan” I want it to say “heat 1tbsp of oil in a pan”. When I shop I need the ingredients but when I’m actually doing the prep I want the directions and quantities at the same time because it’s faster to grab the ingredients and prep them as I go than it is to prep everything and then cook EDIT: no one does this…

I totally agree. I have started working on a recipe website and for my personal recipes this is exactly what I do.

You can see an example of what it looks like for now here: https://www.hedacuisine.com/r/776.

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#26

Post by KMnO4 »

dools wrote: post #9

Sort of minor note but when I cook, I want the directions to contain the quantities. Rather than “heat oil in pan” I want it to say “heat 1tbsp of oil in a pan”. When I shop I need the ingredients but when I’m actually doing the prep I want the directions and quantities at the same time because it’s faster to grab the ingredients and prep them as I go than it is to prep everything and then cook EDIT: no one does this…

I suspect once general NLP models become cheap and widely accessible, we'll see a lot of niche tools that can transform data from one type into another. E.g. you could just paste the recipe in and the tool would already be prompted with "instructions" to output it in the desired format.

Here's ChatGPT's take on the problem, which I think it did pretty well: https://i.ibb.co/dfwVH9G/image.png

Edit - bonus transformation: https://i.ibb.co/7CrKWX7/image.png

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#27

Post by russdill »

dools wrote: post #9

Sort of minor note but when I cook, I want the directions to contain the quantities. Rather than “heat oil in pan” I want it to say “heat 1tbsp of oil in a pan”. When I shop I need the ingredients but when I’m actually doing the prep I want the directions and quantities at the same time because it’s faster to grab the ingredients and prep them as I go than it is to prep everything and then cook EDIT: no one does this…

I mean, ya, that's what you generally want. But oil is a poor example. Are there people out there actually measuring how much oil they put in the pan? It's just a general guideline for if you need a lightly oiled pan, or a pan with a lot of oil. And really the amount of oil you need will vary a lot by the type of pan you are using. A lot of measurements are like this. Like salt, not only are personal tastes very different, but a half teaspoon of one kind of salt can be a lot more salt than a half teaspoon of another type.

Anyway, A lot of people cook by generally knowing good ratios. It takes time though and you can't really get started without explicit measurements.

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#28

Post by TOMDM »

p1necone wrote: post #24
rovr138 wrote: post #6

Earlier quoted context omitted.

Not sure if it was added since, but 7 mins after, it has this, > Quick thanks to Baseten, where I work. As an employee, I had early access to Blueprint where I used their fine-tuning APIs and serverless GPUs, which made this process much faster. You can sign up for the waitlist at: blueprint.baseten.co

Wow, even the disclosure sounds like an ad.

A disclosure ad is fine as long as there is disclosure imo

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#29

Post by jancsika »

TOMDM wrote: post #28
p1necone wrote: post #24

Earlier quoted context omitted.

Wow, even the disclosure sounds like an ad.

A disclosure ad is fine as long as there is disclosure imo

The history of adtech tells me I can pentest "fine" by squashing so many ads into the disclosure that your device starts to get hot.

Re: Show HN: I fine-tuned Flan-T5. Can it cook?

#30

Post by simsspoons »

1024core wrote: post #4

OP does not mention that he's employed by BaseTen, the company behind "Blueprint" (which is mentioned repeatedly in the blog post). I noticed the repeated mentions and did some digging to find this out. Not cool, OP, not cool. See: https://www.baseten.co/blog/deploying-stable-diffusion

relax, it’s just a recipe experiment writeup
Post reply on HN