Depending on the hardware, and next to parameter-efficient finetuning, there are a bunch of memory-lowering techniques you can try. Summarized them here: https://
github.com/rasbt/pytorch-
memory-optim
…
MACHINE LEARNING
-
Memory-Lowering Techniques for PyTorch Hardware Optimization
By
–
-
LLM Guidelines for Training, Finetuning, and Inference
By
–
I am not aware of a guideline, but it usually also depends on what you are after: (pre)training, finetuning, inference. We have a unified codebase for several LLMs you can try here: https://
github.com/Lightning-AI/l
it-gpt
… -
Missing AI meme accounts: discovering ML humor on Threads
By
–
Wondered why my Threads feed was incomplete.
And then I realized i was missing all the vibe accounts…
I've started enjoying the ML memes too much!
@untitled01ipynb @typedfemale @kipperrii @tszzl @repligate -
ViT-everything: Summarizing the main theme
By
–
Thanks! Hah, and to maybe summarize the main theme so far: ViT-everything!
-
CVPR 2023 Main Themes: Vision Transformers, Diffusion Models, NeRFs
By
–
Felt the urge to write about computer vision for a change! Summarizing the main themes from CVPR:
1) Vision transformers
2) Diffusion models
3) NeRFs
4) Object detection & segmentation Recapping it in more detail along with some paper highlights here: -
MindEye: AI Reconstructs Images from Brain fMRI Scans
By
–
Presenting @MedARC_AI
's inaugural research paper, MindEye: an innovative method to retrieve & reconstruct images from fMRI brain scans. Led by @iScienceLuvr
, MedARC is Stability AI's fully supported medical research hub. Stay tuned for more amazing work! -
Predicting Human Behavior with Machine Learning Recommendation Engines
By
–
Predicting Human Behavior #MachineLearning Recommendation Engines #AILabPage #VinsLens @KirkDBorne @SwissCognitive @alvinfoo @mclynd @SpirosMargaris @Fabriziobustama @FrRonconi @enricomolinari @ingliguori @schmarzo @asokan_telecom @SBUCloud @terence_mills
-
Exciting Long-Form Technical Content on AI Fundamentals and Research
By
–
Something that I am super excited about is long-form technical contents grounded on fundamentals and recent advances in AI research. More on this soon and other updates 😀
-
Google and OpenAI Leaders in AI and Machine Learning
By
–
@jeevprabnivash @Google @OpenAI #ai #gpt3 #AImodel #MachineLearning #INDIAai
-
ChatGPT GPT-3 Transformers Revolutionizing NLP Solutions
By
–
Did you know that ChatGPT is based on GPT-3’s language model that uses transformers? Many NLP-based issues are being solved using these advanced methodologies due to the transformer revolution we are experiencing. Want to read more about it? Tap here: https://
rb.gy/kardq