OPEN SOURCE

Low-Cost Privacy-First Project Reaches Technical Limits

By

–

01 April 2024 3h22

I'm pretty much done with it I think – I think this is about as far as I can push it without adding a server-side component, and the whole point of this project is to avoid that and be as low-cost and privacy-friendly as possible

→ View original post on X — @fchollet

Reproducing Benchmarks: Torch Implementations and Performance Comparisons

By

@fchollet

–

01 April 2024 1h25

The code to reproduce the benchmarks yourself is in the link. To note, the native torch implementations used here are well optimized implementations that are widely used. If you compare "plain" implementations (e.g. research code) it's not unusual to see a 5x speedup. I get the

PDF.js Flash code vulnerability investigation

By

–

01 April 2024 1h06

Wait, does PDF.js have Flash code in it then?

→ View original post on X — @gdb

Reference Implementation Clarity Over Specifications

By

@gdb

–

01 April 2024 0h49

a reference implementation, no matter how hacky, often provides more clarity than any spec

Browser OCR Tool Now Supports 102 Tesseract Languages

By

–

01 April 2024 0h39

New feature for my browser-based OCR tool: you can now select the Tesseract.js language to use, from a list of 102 optionshttps://t.co/54uIhZKj2x pic.twitter.com/kVKRIllHMR
— Simon Willison (@simonw) 31 mars 2024

New feature for my browser-based OCR tool: you can now select the Tesseract.js language to use, from a list of 102 options https://
tools.simonwillison.net/ocr

→ View original post on X — @ceobillionaire

Agent Lumos: Unified Modular Training for Open-Source Language Agents

By

@ceobillionaire

–

31 March 2024 18h45

Agent Lumos: Unified and Modular Training for Open-Source Language Agents Yin et al.: https://
arxiv.org/abs/2311.05657 #ArtificialIntelligence #DeepLearning #MachineLearning

→ View original post on X — @gp_pulipaka

Comprehensive List of Machine Learning Algorithms and Tools

By

@gp_pulipaka

–

31 March 2024 18h26

A List of #MachineLearning #Algorithms! #BigData #Analytics #DataScience #AI #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode https://
geni.us/List-of-ML-Know

→ View original post on X — @abhi1thakur

13 Ongoing Competitions Available on Hugging Face

By

@abhi1thakur

–

31 March 2024 17h46

13 ongoing competitions on Hugging Face

E5-Large-V2 and Nomic 1.5 embedding models exploration

By

–

31 March 2024 16h57

I used E5-Large-V2 last year https://
til.simonwillison.net/llms/embed-par
agraphs
… Currently exploring @nomic 1.5: https://
github.com/simonw/llm-nom
ic-api-embed
…