AutoTrain + Unsloth = AutoTrain has now added support for unsloth which means you can use unsloth's optimizations to finetune LLMs super-fast and with much less memory And all you need to do is set unsloth parameter to true P.S. You can use the unsloth param in cli
MACHINE LEARNING
-
PuzzleFusion++ Framework and Breaking Bad Benchmark Release
By
–
Aquí el link al trabajo https://
puzzlefusion-plusplus.github.io También fan de que el benchmark que se usen para esta tarea se llame "Breaking Bad" -
Diffusion Models Reconstruct Fragmented 3D Objects
By
–
Qué chulo este trabajo que usa modelos de difusión para reconstruir objetos tridimensionales fragmentados y resolver el puzzle de armarlos.pic.twitter.com/KlvOxvlbqp
— Carlos Santana (@DotCSV) 11 juin 2024Qué chulo este trabajo que usa modelos de difusión para reconstruir objetos tridimensionales fragmentados y resolver el puzzle de armarlos.
-
Indie Developer Releases Graph Neural Networks Book
By
–
I've spent 15 years making indie video games but my first release on Humble Bundle is my book about Graph Neural Networks. Please support your local indie GNN developer https://
humblebundle.com/books/generati
ve-ai-packt-books
… -
CVPR Keynote on Affective Behavior Analysis Workshop
By
–
Excited to attend @CVPR next week and give a keynote at Affective Behavior Analysis in the Wild workshop. It would be great to catch up if you're around!
-
3B Parameters Model Memory Requirements Discussion
By
–
3B parameters right? where do we get 30-40gb from?
-
AI Models Should Be Capable of Diverse Thinking
By
–
I want my AI models to be able to think different.
-
Probability Decreases Exponentially with Increasing Dimensions
By
–
Probability goes down exponentially with no. dimensions.
-
Semantic Indexing and Vector Databases in AI Systems
By
–
semantic index sounds a whole lot like a vector database tbh
-
Plateaus, Not Minima, Are Gradient Descent’s Real Challenge
By
–
The real problem in gradient descent isn’t local minima, because they’re extremely rare. It’s not saddle points either, because any small amount of noise gets you out of them. The real problem is plateaus.