Login

Recent searches

No recent searches

Search options

Not available on writing.exchange.
writing.exchange is one of the many independent Mastodon servers you can use to participate in the fediverse.
A small, intentional community for poets, authors, and every kind of writer.

Administered by:

Server stats:

324
active users

writing.exchange: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#huggingface

1 post1 participant0 posts today
Replied in thread
Public
R.L. Dane :Debian: :OpenBSD: 🍵

@justine

You know, I think recent versions of iOS do lots of (fairly good, apparently) OCR on the fly when handling images, so I think people are unlearning the difference between images and text.

Oh, woe. XD XD XD

FOSS Android only has very poor/limited (tesseract-based, probably) OCR options. Maybe we'll get some "AI"-based OCR options in the near future, like how woheller69 has added a bunch of #huggingface-based AI apps to F-Droid, like a speech to text app and a birdsong recognizer.

Public
sc0v0ne

MCP, Agentic Knowledge Graphs & AI Models: Solving Conversational Analytics

eventbrite.com/e/mcp-agentic-k

In this free webinar led by ex-Snowflake, Cloudera, and Amazon leaders, we'll unveil how cutting-edge LLMs (GPT 4.5, Sonnet 3.7, Deepseek V3/R1, Gemini 2.5, etc.) are revolutionizing data products.
#python #machinelearning #deeplearning #ai #developer #dev #devsecops #devops #mlops #learn #learning #study #git #github #codeberg #tensorflow #pytorch #jax #huggingface #linux #ubuntu #popos #llm

EventbriteMCP, Agentic Knowledge Graphs & AI Models: Solving Conversational AnalyticsCo-hosted by Gunther Hagleitner and Wangda Tan, former engineering and product leaders at Snowflake, Cloudera, & Cribl. Founders of Waii.ai.
Public
Sarah Lea

Wow, three of my Medium articles have been boosted in a row - thank you all for reading and sharing! 🙌

If you don't know the articles yet, here are the friend links:
:blobcoffee: How to Try Out an Open-Source AI Model Without Costly Hardware

A practical guide on how you can easily test an open-source language model like IBM Granite with Hugging Face Spaces and Gradio.

👉 medium.com/data-science-collec

:blobcoffee: 5 Important Lessons I Learned as a Tech Consultant over the Last 5 Years

Underestimated skills in IT consulting - and what I've learned from them.

👉 code.likeagirl.io/5-important-

:blobcoffee: How to Skip the AI Hype and Find Reliable Expert Information

How to find high-quality content about AI and avoid information overload.

👉 medium.com/data-science-collec

Enjoy reading :blobcoffee:

#llm #opensource #Huggingface #ibm #python #ai #consultant #technology #IT #support #career #careeradvice #customerexperience #productivity
#learning #machinelearning #deeplearning #datascience #datascientist

Data Science Collective · How to Try Out an Open-Source AI Model Without Costly HardwareBy Sarah Lea
Public
Jesus Castagnetto 🇵🇪

And ultra compact #AI model for document #OCR by #IBM and #HuggingFace

marktechpost.com/2025/03/18/ib

MarkTechPost · IBM and Hugging Face Researchers Release SmolDocling: A 256M Open-Source Vision Language Model for Complete Document OCRConverting complex documents into structured data has long posed significant challenges in the field of computer science. Traditional approaches, involving ensemble systems or very large foundational models, often encounter substantial hurdles such as difficulty in fine-tuning, generalization issues, hallucinations, and high computational costs. Ensemble systems, though efficient for specific tasks, frequently fail to generalize due to their dependency on handcrafted pipelines for each sub-task. On the other hand, multimodal foundational models, although powerful, often suffer from high computational costs and reliability issues like hallucinations. Researchers from IBM and Hugging Face have recently addressed these challenges by releasing SmolDocling, a 256M
Public
Technology Tales

Explore #HuggingFace's new #AI framework, #smolagents! 🚀 This lightweight library simplifies AI agent development using minimal code. Compatible with many LLMs and supporting various input types, smolagents streamlines tasks, offering a practical approach to building Multi-Agent Systems for enhanced problem-solving. Discover more about these advanced AI tools. #MachineLearning #TechNews kdnuggets.com/big-gains-with-h

Public
arXiv

This post is for the night owls . . . #GivingDay is officially LIVE! 🦉🌜

The sun may not be up, but it's never too late (or too early) to support arXiv. And for the next 24 hours, our friends at #HuggingFace are TRIPLING your donations with a 2:1 match.

AKA when you give $1, Hugging Face gives $2, and arXiv gets $3 of support for #openscience!

Give today and make a difference in the future of scientific research and #openaccess:

🤗❤️👉 givingday.cornell.edu/campaign

ExploreLive feeds
About