Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Advanced Hashrate Hedging Strategies for Professional Bitcoin Mining Companies

Thumbnail of www-x-com-tom-doerr-status-1856108385965355502-b725f57803bd4df1

For people who like RAG and Moo Deng - "🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library" https://t.co/GyNs6KWqky

Tom Dörr

x.com

The no-nonsense chunking library. Lightweight, lightning fast and prepared to Chonk all your docs 🦛 ✨ https://t.co/0nRUcFrUeN... See more

Chonkie

x.com

Convert PDFs to machine-readable formatslike markdown or JSON for easy data extraction https://t.co/e6H7TSkqmM

Tom Dörr

x.com

🌵LangChain x GPTCache🌵 Caching can be useful in certain situations to save money on repeated LLM calls GPTCache is a project that caches requests/responses not only the exact prompt, but based on semantic similarity. h/t Frank Liu for adding Docs: https://t.co/pm1ubEldYV

LangChain x.com

@acrognali Entropix style sampler, all exponentials at fp32, fused MoE, etc

xjdr x.com

Independent hashing means applying the hash function to each piece of data independently.

Daniel Drescher • Blockchain Basics: A Non-Technical Introduction in 25 Steps

Thumbnail of www-x-com-willccbb-status-1919072806886674472-0a3e55a7ca394f40

a technique i'm increasingly believing is going to be really useful in large-scale synth data pipelines is the use of graph algorithms to do semantic deduplication submitted a paper about this a while back, never got around to cleaning it up for arxiv, but it's a neat trick https://t.co/XNVRTWxCSq

will brown

x.com

Scattered Mixture-of-Experts Implementation - Presents ScatterMoE, an implementation of Sparse Mixture-of-Experts on GPU - Enables a higher throughput and lower memory footprint repo: https://t.co/kJZjY6Q4O7 abs:... See more

Aran Komatsuzaki

x.com