@giffmana@DavidBeniaguev@yacineMTB Thanks for sharing, I’ll try these and see how it goes. I’ve had good results back by using OWLViT as a visual prompt engine and then feeding the results into something like SAM if I want segmentations.
Sometimes it’s easier to describe an object by an image rather than text
Hot take 🔥: Lots of buzz these days about new foundation open-source models but what if I told you there have been no real advance since 2019's T5 models 😀
Take a look at this table from this new InstructEval paper: https://t.co/Pe3ajGtavs. Some thoughts/observations:
1. Flan-T5 beats everything, including Alpaca (LLama-based), Flan-Alpaca, Mosiac-Chat/MPT, Dolly.
2. If you arrange this table in terms of "compute-match", encoder-decoder should have been in a different (lower) weight class. Basically, Flan-T5 3B is like a 1B+ decoder and Flan-UL2 is more like a 8B+ model. With this perspective, the gap is so dramatically huge that it's not even funny.
3. Flan-UL2 basically wrecks Alpaca-Lora 30B despite being so much smaller and effectively 4x less compute.
4. This is not entirely about Flan series models - it's more about the base models! The point is that the base T5 models are already ridiculously strong. 1 trillion tokens, just blatantly repeating C4 to heart's content. There's also mT5 and uMT5 which are strongly multilingual and ridiculously good. The base models are not long context, but Flan mitigates this.
5. The weakness is that T5/UL2 models are not diverse and are only C4 trained that means they probably don't do well at code/math whatever (code eval 0 score below lol). But its scary how strong a C4-only baseline that we had since 2019 is performing.
6. If you look at fastchat-t5 on the chatbot arena by @lmsysorg the 3B fastchat model does as well as MPT-7B et al despite being only 3B (and if you paid attention till now you know that's a 1B+ equivalent decoder-only model). That's really insane if you think of a 1B+ model on a leaderboard of all these new "OSS LLM advances".
7. It's likely at compute match, T5 >> Llama. The only problem is that we don't have T5 models at 30B and 65B.
You're welcome.
@senlog Depends on the university, they all have different ROI. Also ROI highly depends on yourself, so think of whether you’ll actually make it worth it or you just want a piece of paper with your name and degree in it
@senlog EU has pretty good work life balance. Health insurance is free but it can suck, depending on what you’re used to. Growth it’s ok, hard to find something better than the USA tho