Articles for category: AI Tools

March 28, 2025

ikayaniaamirshahzad@gmail.com

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B

Today, integrating AI-powered features, particularly leveraging Large Language Models (LLMs), has become increasingly prevalent across various tasks such as text generation, classification, image-to-text, image-to-image transformations, etc. Developers are increasingly recognizing these applications’ potential benefits, particularly in enhancing core tasks such as scriptwriting, web development, and, now, interfacing with data. Historically, crafting insightful SQL queries for data analysis was primarily the domain of data analysts, SQL developers, data engineers, or professionals in related fields, all navigating the nuances of SQL dialect syntax. However, with the advent of AI-powered solutions, the landscape is evolving. These advanced models offer new avenues for interacting

March 28, 2025

ikayaniaamirshahzad@gmail.com

Tailwind CSS: A Beginner’s Guide to Understanding Its Syntax and Structure

Introduction: How I Discovered Tailwind CSS I’ve always been more comfortable working with backend development—APIs, databases, and server-side logic. Styling, on the other hand, always felt like an entirely different world. Writing raw CSS meant managing stylesheets, worrying about specificity, and dealing with unpredictable layouts. Even CSS frameworks like Bootstrap felt too rigid for me. Then I discovered Tailwind CSS, and I was like—”OK, this is something I can work with!” It had a common syntax and a one-for-all structure that made sense. Instead of switching between multiple files, naming classes, and dealing with stylesheet bloat, I could just use

March 28, 2025

ikayaniaamirshahzad@gmail.com

Serving Qwen Models on Databricks

Qwen models, developed by Alibaba, have shown strong performance in both code completion and instruction tasks. In this blog, we’ll show how you can register and deploy Qwen models on Databricks using an approach similar to that for Llama-based architectures. By following these steps, you can take advantage of Databricks’ foundation model (Provisioned Throughput) endpoints, which benefit from low latency and high throughput. Table of Contents Motivation: Why Serve Qwen Models on Databricks? The Core Idea Implementation: Annotated Code Walkthrough Performance and Limitations Summary and Next Steps Motivation: Why Serve Qwen Models on Databricks? For many enterprise workloads, Databricks is

March 28, 2025

ikayaniaamirshahzad@gmail.com

End-to-end Neural Coreference Resolution in spaCy · Explosion

Coreference resolution is something all of us do instinctively many times every day even though most of us haven’t heard the term before. People use language to talk about entities, events and the relationships between them. When we mention the same thing multiple times throughout a discourse we tend to use different expressions. For example: Here “the bass” and “it” refer to the same entity. Within natural language processing, coreference resolution is a core task that helps with a large array of tasks ranging from machine translation all the way to information extraction. In this post we will introduce spaCy’s

March 28, 2025

ikayaniaamirshahzad@gmail.com

Hugging Face partners with Wiz Research to Improve AI Security

We are pleased to announce that we are partnering with Wiz with the goal of improving security across our platform and the AI/ML ecosystem at large. Wiz researchers collaborated with Hugging Face on the security of our platform and shared their findings. Wiz is a cloud security company that helps their customers build and maintain software in a secure manner. Along with the publication of this research, we are taking the opportunity to highlight some related Hugging Face security improvements. Hugging Face has recently integrated Wiz for Vulnerability Management, a continuous and proactive process to keep our platform free of

March 28, 2025

ikayaniaamirshahzad@gmail.com

Mastering CSS Float Property for Modern Layouts

This post was originally published at thedevspace.io. Everything you need to master web development, all in one place. Originally, the float property was used to take an HTML element (usually an image) out of the normal flow of the webpage and make it float on top of other elements. But then developers quickly realized you can use float to design entire webpage layouts, so that multiple columns of information could sit next to each other. However, with the creation of modern layout techniques such as grid and flexbox, float gradually returned to its original purpose. Float Here is an example

March 28, 2025

ikayaniaamirshahzad@gmail.com

How the Guardian approaches quote extraction with NLP · Explosion

A recent trend for media companies is to explore how fields like Natural Language Processing (NLP) and Information Extraction (IE) can modularize content like a long-form article as reusable elements for different storytelling formats (e.g., a podcast, information graphic, or blog). This push is called modular journalism and many media companies are building towards it to automate customized stories to meet individual user needs for a variety of media forms. The Guardian explored quote extraction with the goal of modular journalism to reuse quotes from long articles for different media artifacts like podcasts or information graphics. At the same time,

March 28, 2025

ikayaniaamirshahzad@gmail.com

Public Policy at Hugging Face

AI Policy at Hugging Face is a multidisciplinary and cross-organizational workstream. Instead of being part of a vertical communications or global affairs organization, our policy work is rooted in the expertise of our many researchers and developers, from Ethics and Society Regulars and the legal team to machine learning engineers working on healthcare, art, and evaluations. What we work on is informed by our Hugging Face community needs and experiences on the Hub. We champion responsible openness, investing heavily in ethics-forward research, transparency mechanisms, platform safeguards, and translate our lessons to policy. So what have we shared with policymakers? Policy

March 28, 2025

ikayaniaamirshahzad@gmail.com

DataScience SG Meetup – How we got top 3% in Kaggle

One Saturday afternoon, I volunteered to share about my recent effort in Kaggle’s Otto competition where I placed 85th / 3514 with my fellow competitor Weimin. Given that it was a lazy Saturday afternoon, I did not expect the lecture room at SMU to be fully packed. The data science meetup scene in Singapore was more vibrant and hotter than I thought. In approximately 45 minutes, we shared about how we thought about and had an in-depth discussion with the audience on the topics below: The evaluation metric (multi-class log loss) Validation approaches Feature engineering and selection Feature transformation (e.g.,

March 28, 2025

ikayaniaamirshahzad@gmail.com

zkTLS with Oasis Sapphire: Verifiable and Private Web3 for Developers

Web traffic is encrypted with TLS(Transport Layer Security), but can you prove that it’s secure? zkTLS introduces zero-knowledge proofs (ZKPs) that allow verifiable TLS interactions without exposing sensitive data. Why zkTLS is Transformational → Verifiable TLS – Cryptographically prove that the TLS handshake followed the protocol without revealing sensitive data.→ Zero-Leak Privacy – Prove the correctness of encrypted communication without disclosing session details.→ Secure and Efficient – Reduce on-chain costs by moving heavy cryptographic computations off-chain. Oasis Sapphire: Enhancing zkTLS with Confidential Smart Contracts Oasis Sapphire adds: Confidential Computation with TEEs – Protects sensitive contract logic and data. On-Chain Verifiability