81–90 of 98 posts
(Disclaimer: I'm the founder of OpenPipe, one of the fine-tuning services OP tried and ultimately the one that produced the highest performing model, it appears.) Data extraction is a use case that fine-tuned models are fantastic at, so I'm not surprised that OP got good results. That said, I've also found it's pretty easy to beat GPT-4 across many task types if you have a way of getting strong training data. We publ…
Earlier quoted context omitted.
The way you cut that quote turns it into an assertion that doesn't exist in parent post. They didn't make the (incorrect) statement that no other serious, useful application exists. But that's how it reads when you cut off before "I have actually engaged in for real work and found useful"
To be fair the original sentence could still be implying the same thing. The second half of the sentence just sounds like a hedge.
(Disclaimer: I'm the founder of OpenPipe, one of the fine-tuning services OP tried and ultimately the one that produced the highest performing model, it appears.) Data extraction is a use case that fine-tuned models are fantastic at, so I'm not surprised that OP got good results. That said, I've also found it's pretty easy to beat GPT-4 across many task types if you have a way of getting strong training data. We publ…
Is this something, as a tech enthusiast that's no expert, I can easily fine tune are run? My use case would be fine tuning on technical docs. Specific news, 2 years of blog posts, primary source material, and Twitter explainer thread. I want to gather all the niche information of a topic from the last two years, dump it into this and have an LLM that is a subject-matter expert.
And that’s the point of fine tuning models. Still good to see someone walk through their fine tuning process, with a mix of hosted and local options.
On that note: is there a good service for “here’s my dataset”, please fine tune these 9 models and give me evaluation stats?
85% of the time they beat GPT-4.
You can see the results here: https://predibase.com/fine-tuning-index.
The site has a series of interactive charts and a link to our Arxiv paper.
(Disclaimer: I'm the founder of OpenPipe, one of the fine-tuning services OP tried and ultimately the one that produced the highest performing model, it appears.) Data extraction is a use case that fine-tuned models are fantastic at, so I'm not surprised that OP got good results. That said, I've also found it's pretty easy to beat GPT-4 across many task types if you have a way of getting strong training data. We publ…
Is this something, as a tech enthusiast that's no expert, I can easily fine tune are run? My use case would be fine tuning on technical docs. Specific news, 2 years of blog posts, primary source material, and Twitter explainer thread. I want to gather all the niche information of a topic from the last two years, dump it into this and have an LLM that is a subject-matter expert.
Your use case is better suited to RAG. This is where you retrieve data from a large dataset and inject it into the user's request so the AI model has the context it needs to answer accurately.
But that's not a silver bullet and you would need to spend significant time on chunking strategy and ranking of results to hopefully get a decent response accuracy.
Earlier quoted context omitted.
It seems to me this means whoever has hoarded and declared ownership of the most personal data will make the best products. Kinda like how some people liked their targeted ads because they’re more “relevant”, only now it’s not just ads but useful products. Another winner is of course platform owners like Apple and Microsoft who can scrape your data off their apps and products, even locally. This is a much bigger edge…
Your end point I think is exactly right. I think your first one is getting downvoted hard because your first sentence is not at all how any of this works. Sucking down personal data isn't JUST a bad idea for privacy, it's actually also bad for "making the best products," I think you're overstating the extent to which all that data that is stolen and sold to the highest bidder actually helps the company buying it?
> data that is stolen and sold to the highest bidder
Didn’t mean necessarily the data brokers (although that’s an interesting angle), but say Apple now has a bunch of info about your calendar, email, contacts, then clearly they have an upper hand in providing better products than an anonymous API call. Not all products need personalization but LLMs? I can think of tons of use cases.
The hype is really getting tiresome. There is no way to get from here to any intelligent system with the current techniques. New breakthroughs will require insights into discrete spaces which are not amenable to curve fitting with gradient descent.