llama_person
llama_person on Hacker News
I bought Sublime with my first developer paycheck, eons ago. Thanks for your great work <3.
They got me a stellar job many years ago, but unfortunately for them it's hard to monetize candidates unless they return through the same pipeline. My outcome was great, but I was one and done.
Same here, it's tons of work to collect, clean, validate data, followed by a tiny fun portion where you train models, then you do the whole loop over again.
If you have access to a GPU, try a vision-language model using Ollama, and feed it your notes. Might work out!
Looking forward to it, very happy customer!
How's the battery on this one? I'm hoping to upgrade from 11th gen intel i7. If possible, upgrading by just swapping the mainboard would be amazing.
you can try out
https://huggingface.co/datasets/BAAI/SVIT which appears to support commercial. I've not tried it yet, but it seems to be an option.
If you build a smaller model, you should need much less than 18 A100s for 24 hours, though I don't disagree you'll need at least a few.
There are advantages to smaller models, namely you can process a lot more data, with a lot less vram. I think the intent here from the Google team is for a task-specific VLM that you fine-tune on your data, rather than a general purpose assistant.
From my own experimentation I have found it to really pack a punch for its weight. Another small model which has been very good has been https://github.com/vikhyat/moondream .
One more opinion here: if you're looking around and nobody else has something obviously working, it's ok not to do a thorough search through hundreds of papers hoping to find someone else who came up with the idea. Get it working first, show it off, and if someone comes claiming it was their idea, respectfully acknowledge the prior work. But there's a gigantic gap between "wrote it in a paper" and "actually got it working".
Also, awesome job! Thanks for writing up some seriously cool engineering.