Viewing profile — convexstrictly

Tokenization is done on the CPU. Models never see the raw characters. That's why you get trick questions like the number of r's in strawberry. There are many research papers on mod…

GitHub: https://github.com/marcelroed/gigatoken

Video Demo: https://x.com/OfficialLoganK/status/1869789822384255300

"Just when you thought it was over... we’re introducing Gemini 2.0 Flash Thinking, a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The…

GB per second

Simran Arora: "Join us for a livestream this Thursday, Halloween/Diwali , and join our channel on the GPU Mode Discord server to hang out with us/get involved:" https://discord.com…

CUDA + ThunderKittens 4.5 hour tutorial https://www.youtube.com/watch?v=xcpEl0cGCC4

Results https://x.com/sbeastwindy/status/1801525876267372874

Aider uses Treesitter to improve code generation. https://aider.chat/2023/10/22/repomap.html Aider: https://github.com/paul-gauthier/aider It is state of the art on SWE-Bench and S…

Candle is a minimalist ML framework for Rust with a focus on performance (including GPU support) and ease of use https://github.com/huggingface/candle

An author claims better performance than LoRA in 50% of the time. https://twitter.com/Rui45898440/status/1772996453557997924

The federal government requests comments on regulation of AI models with openly available weights. The deadline is March 27, 2024. Earlier thread. https://news.ycombinator.com/item…