March 28, 2025
spaCy Cheat Sheet
Everything you need to know about spaCy as a handy two-page PDF. Source link
Articles for category: AI Tools
March 28, 2025
an official Google release for code LLMs
CodeGemma is a family of open-access versions of Gemma specialized in code, and we’re excited to collaborate with Google on its release to make it as accessible as possible.🤗 CodeGemma comes in three flavors: A 2B base model specialized in infilling and open-ended generation. A 7B base model trained with both code infilling and natural language. A 7B instruct model a user can chat with about code. We’ve collaborated with Google to ensure the best integration into the Hugging Face ecosystem. You can find the three open-access models ready to use on the Hub. Among the features and integrations being
March 28, 2025
DataKind Singapore’s Latest Project Accelerator
Originally posted on DataKind’s blog. From providing clean water and sanitation to fighting human trafficking to improving the lives of the underserved, nonprofits in our region are collecting a lot of useful data that could help inform their work and better serve their communities. However, many don’t have the time or staff expertise to clean, analyze, and visualize the data to take advantage of this powerful resource. During DataKind Singapore’s third Project Accelerator, over 40 volunteer data scientists came together for a night of brainstorming and consulting to help four local organizations do just this. Representatives from Lien AID, Phandeeyar,
March 28, 2025
Struggling with Your Productivity Stack? Here’s My $0 Solution!
Over the last few months, I kept bouncing between Notion, Trello, and half a dozen other “productivity suites.” None of them stuck. Turns out, I was overcomplicating it. Here’s how I simplified my productivity stack (and kept it under $0): Created a simple Kanban board using GitHub Projects. Used Markdown + VS Code for my notes (no more cluttered apps). Integrated everything into one README dashboard. If you feel overwhelmed by tools, try this. It might just save your sanity. Having said that, my techy side loves an automation.🔥 Your co-devs will swear you’ve unlocked a 36-hour day… If you’re
March 28, 2025
medspacy/medspacy: Library for clinical NLP with spaCy.
Library for clinical NLP with spaCy. MedSpaCy is currently in beta. MedSpaCy is a library of tools for performing clinical NLP and text processing tasks with the popular spaCy framework. The medspacy package brings together a number of other packages, each of which implements specific functionality for common clinical text processing specific to the clinical domain, such as sentence segmentation, contextual analysis and attribute assertion, and section detection. medspacy is modularized so that each component can be used independently. All of medspacy is designed to be used as part of a spacy processing pipeline. Each of the following modules is
March 28, 2025
Making thousands of open LLMs bloom in the Vertex AI Model Garden
Today, we are thrilled to announce the launch of Deploy on Google Cloud, a new integration on the Hugging Face Hub to deploy thousands of foundation models easily to Google Cloud using Vertex AI or Google Kubernetes Engine (GKE). Deploy on Google Cloud makes it easy to deploy open models as API Endpoints within your own Google Cloud account, either directly through Hugging Face model cards or within Vertex Model Garden, Google Cloud’s single place to discover, customize, and deploy a wide variety of models from Google and Google partners. Starting today, we are enabling the most popular open models
March 28, 2025
Quoting Colin Fraser
Slop is about collapsing to the mode. It’s about information heat death. It’s lukewarm emptiness. It’s ten million approximately identical cartoon selfies that no one will ever recall in detail because none of the details matter. — Colin Fraser Tags: ai-ethics, slop, ai, generative-ai Source link
March 28, 2025
First post!
Writing is not as romantic as this images makes it out to be. Update: Today, it’s 2020-06-11, almost four years since I started. I’m converting this old HTML post into Jekyll now. Wow, what a journey it’s been. I’ve finally decided to buckle down and start writing, with the main intent of practising (and hopefully, improving) my writing. Let’s see how far we get. If you found this useful, please cite this write-up as: Yan, Ziyou. (Jul 2016). First post!. eugeneyan.com. https://eugeneyan.com/writing/first-post/. or @article{yan2016first, title = {First post!}, author = {Yan, Ziyou}, journal = {eugeneyan.com}, year = {2016}, month =
March 28, 2025
AWS open source newsletter, #208
Welcome to issue #208 of the AWS open source newsletter, the newsletter where we try and provide you the best open source on AWS content. As always, we have more great new projects to check out, which include an experimental profiler for your serverless Java applications, a bunch of cool projects around Model Context Protocol (MCP), an interesting project around extracting insights from your observation data, projects to help you with your AWS storage services, an interesting project for those of you exploring chaos engineering, some nice generative AI projects that help you explore your code base, and to finish,
March 28, 2025
Finetuning and Bulk Labelling Images with Prodigy
In this video, we’ll show how you might be able to improve the annotation experience by using bulk labelling for image classification. Source link