It’s whatever the byte-pair encoding algorithm says which depends on the pre-train statistics. There are many shorter ones too — the top 130 longest tokens are all banners and whitespace of various lengths.
TECHNOLOGY
-
CEO to discuss AI, ML, and security at TechTour Growth50
By
–
Join us next week as our CEO and Co-Founder, @FabAroundEU
, participates in @TechTourHQ Growth50 Europe 2024 event in Paris, France. He will be featured on a panel discussing AI, ML, and security on February 8 at 11:15 CET.
Learn more here
https://
lnkd.in/dUf569Ey -
Imagen2 Model for Image Generation Explained
By
–
Lumiere is for video. This is just images. It's using the Imagen2 model.
-
Meta Deploys Artemis AI Chip to Reduce NVIDIA GPU Reliance
By
–
Meta released plans to deploy its 2nd-gen custom AI chip, codenamed "Artemis". The chip will be integrated into data centers as soon as this year to reduce reliance on costly NVIDIA GPUs. Meta is making big bets on AI.
-
EA CEO Discusses Sports Metaverse Vision and Strategy
By
–
EA CEO shares his thoughts on a sports #Metaverse https://
venturebeat.com/games/ea-ceo-s
hares-his-thoughts-on-a-sports-metaverse/
… via @VentureBeat -
Exponential Technology Acceleration: 15 Years Compressed to Months
By
–
The technology is exponential. What used to take 15-years will likely now take 15-months (or less).
-
Read Write Own U.K. Launch Expands Crypto Blockchain Interest
By
–
Our book launch week continues — the U.K. edition of Read Write Own is available starting today. It’s been exciting to see all the positive energy at our U.S. launch events so far. Interest in crypto and blockchains continues to build around the world, so we’ll continue
-
LangServe Frontend Integration with React and Tailwind CSS
By
–
Chat With Your PDF Pt 2 of this series by @austinbv focuses on how to hook LangServe up to a full frontend Utilizes @tailwindcss and @reactjs Handles streaming of tokens & showing the retrieved documents
-
MobileDiffusion enables rapid on-device text-to-image generation
By
–
Check out MobileDiffusion’s potential for rapid text-to-image on-device in testing, shown below: pic.twitter.com/33Ng2it3oF
— Google AI (@GoogleAI) 1 février 2024Check out MobileDiffusion’s potential for rapid text-to-image on-device in testing, shown below: