BFloat16 is a format introduced in Ampere architectures (Nvidia A100 cards) or newer. M1 chips for some reason have also bfloat16 in PyTorch, but I think this MPS bfloat16 is something very different.
MACHINE LEARNING
-
BFloat16 Weight Clipping Limits and Extreme Value Representation
By
–
Hm, so that means all weights above values 65504 and below -65504 will be clipped. Does anyone know of there are numbers that large/small in the original bfloat16 representation?
-
Natural Language Processing Course UT Austin Lecture Videos and Materials
By
–
Natural Language Processing – UT Austin Lecture videos: https://
youtube.com/playlist?list=
PLofp2YXfp7TZZ5c7HEChs0_wfEfewLDs7
… Website(for slides, readings): https://
cs.utexas.edu/~gdurrett/cour
ses/online-course/materials.html
… -
UT Austin NLP Lectures: From Basics to LLMs and Beyond
By
–
Natural Language Processing – UT Austin A concise series of NLP lectures from UT Austin. Covers a vector of topics from basics of machine learning, NLP fundamentals, models(BERT, BART, T5, GPT-3…), and hot topics/trends in LLMs including instruction tuning, chain-of-thoughts,
-
Self-driving cars progress and future challenges discussion
By
–
Interesting discussion of past and future of self-driving cars with
@CadeMetz
. Engineers have made remarkable progress, but much remains to be done… -
Golf Analytics: Data-Driven Approach Transforms Game Strategy
By
–
Golfers used to take a "hit and hope" approach when playing a course, but Martin Trainer, PGA Pro, uses analytics to consider the physical characteristics and weather – it can make all the difference. Read on: https://
ow.ly/TOLM50PC0bO #GolfAnalytics #AlteryxFanalytics -
AI Revolutionizing Astronomical Research and Universe Study
By
–
How AI is helping astronomers study the universe
#AI #AIio #BigData #ML #NLU #Futureofwork @briansolis @Xbond49 @VitalikButerin @DataScienceCtrl @Benioff @johnnosta @IrmaRaste @Tiffani_Bova http://
ow.ly/3FgQ30swOv7 -
New LLM Survey Report on Production Adoption and Customization Techniques
By
–
Check out our new #LLM survey report to get a lowdown on the current state of LLMs in #production. Topics covered: LLM adoption Top use cases Key challenges when productionizing LLMs Techniques for customization incl. #finetuning and more! https://
pbase.ai/44jLmba. -
Data Science and AI Interview with Sean Taylor from Motif Analytics
By
–
Data Science and AI with Sean Taylor (Chief Scientist at Motif Analytics, previously Data Science @ Facebook, Lyft) https://
spoti.fi/3qn77ZC #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Milvus Vector Store Integration Brings Trillion-Scale Indexing
By
–
🍃 Milvus Vector Store@milvusio is specifically designed to handle queries over input vectors, and capable of indexing vectors on a trillion scale.
— FlowiseAI (@FlowiseAI) 23 août 2023
Excited to have them on Flowise! pic.twitter.com/6chKdBEbLdMilvus Vector Store @milvusio is specifically designed to handle queries over input vectors, and capable of indexing vectors on a trillion scale. Excited to have them on Flowise!