Ryan Avery

Possibly relevant? I think the authors make a good case for focusing efforts on improving vision representations in multi modal llms to make truly flexible models in terms of accepted...

https://x.com/osanseviero/status/1807679660328620099 ^ Possible funding source for model distillation work.

Curious why CC-By is a blocker? this article indicates that the model can be used, even commercially, with attribution. https://satellogic.com/2024/05/01/satellogic-open-source-release-a-large-dataset-of-high-resolution-imagery-for-ai-model-training/ For any high res dataset sourced from a commercial provider,...

Thanks @joh4nd for this PR. My initial instinct is to provide just one way to do the setup so that everyone in the workshop can follow the same instructions for...

From my past experience teaching these workshops, most learners are grad students or others in academia who aren't familiar with docker. I lean toward not including these instructions in the...

I'm going to close this since I think folks who have taught this are in agreement. Thank you for sharing it though @joh4nd.

bump! curious if these concerns have been looked at. The results were recently presented at Ray Summit 2024 but these concerns were not discussed in the presentation, just the original...

Thanks @amogkam ! I do think that the 17x sagemaker performance multiple might fall quite steeply if cluster startup and docker pull are included. Curious if plans come up for...

Gotcha, I think this is particularly useful when running remote workshops and this would be a great addition to the lesson.

@lxning I'll test again. Both @weiji14 and I ran into the same issue with this demo last week, following the same steps.