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

Bagel: Open-source unified multimodal model

bagel-ai.org

Post reply on HN
Print view View original

21–30 of 35 posts

Re: Bagel: Open-source unified multimodal model

#23

Post by rvnx »

pleone wrote: post #18

Is it from ByteDance Team, right? The team behind TikTok, CapCut, BuzzVideo and more. Any thoughts on that?

Like BYD vs Tesla. US is getting more and more late and more closed than ever (e.g. Chinese Qwen LLM versus LLaMA). So long-term, China may emerge as the dominating force in tech.

Re: Bagel: Open-source unified multimodal model

#25

Post by jxjnskkzxxhx »

kleiba wrote: post #14
jxjnskkzxxhx wrote: post #9

Earlier quoted context omitted.

As someone who used to be in the academia, I think is isn't bad in itself , I just worry that by comparison it raises the burden of effort that one has to make in order to get their work noticed.

Compared to the effort required to play in that field at all , making a video is almost negligible.

If it's an obligation, it's admin. Scientists hate admin.

Re: Bagel: Open-source unified multimodal model

#26

Post by jjrv »

I found a losslessly compressed version: https://github.com/LeanModels/Bagel-DFloat11

It works following readme instructions at least on Ubuntu, on my RTX 3090 GPU with 24 gigs of memory, just barely. Have to close most other windows and lower screen resolution to be able to load the model. Then it generates or edits images in 2-3 minutes. I only have this one GPU and am using Chrome to use the browser interface on the same machine.

The original release won't run on this hardware, but the compressed one is supposed to give identical results.

Re: Bagel: Open-source unified multimodal model

#27

Post by jjrv »

jjrv wrote: post #26

I found a losslessly compressed version: https://github.com/LeanModels/Bagel-DFloat11 It works following readme instructions at least on Ubuntu, on my RTX 3090 GPU with 24 gigs of memory, just barely. Have to close most other windows and lower screen resolution to be able to load the model. Then it generates or edits images in 2-3 minutes. I only have this one GPU and am using Chrome to use the browser interface on t…

I also asked it to explain what's funny in some newspaper comic strips in Finnish. It misunderstands some words and makes up nutty explanations, but most phrases still get translated correctly and its explanations do fit the drawn scenes once you factor in those misunderstandings. For such a small model that seemed impressive.
Post reply on HN