Articles for category: AI Tools

March 29, 2025

ikayaniaamirshahzad@gmail.com

an end-to-end example with Vectara’s hallucination leaderboard

Hugging Face’s Open LLM Leaderboard (originally created by Ed Beeching and Lewis Tunstall, and maintained by Nathan Habib and Clémentine Fourrier) is well known for tracking the performance of open source LLMs, comparing their performance in a variety of tasks, such as TruthfulQA or HellaSwag. This has been of tremendous value to the open-source community, as it provides a way for practitioners to keep track of the best open-source models. In late 2023, at Vectara we introduced the Hughes Hallucination Evaluation Model (HHEM), an open-source model for measuring the extent to which an LLM hallucinates (generates text that is nonsensical

March 29, 2025

ikayaniaamirshahzad@gmail.com

Wireframing for Beginners – 10 Tips to Get Started

Introduction – Why Wireframing is Essential Wireframing is one of the most important steps in UI/UX design, allowing designers, developers, and product teams to visualize layouts and user flows before diving into high-fidelity design or development. If you’re new to wireframing, you might wonder where to start. What tools should you use? How detailed should your wireframes be? What are the common mistakes to avoid? In this guide, we’ll cover 10 essential tips to help beginners create effective, structured, and user-friendly wireframes. 1. Start with Low-Fidelity Wireframes Why? Low-fidelity wireframes are quick sketches that help focus on layout and functionality

March 29, 2025

ikayaniaamirshahzad@gmail.com

Applied NLP Thinking – Speaker Deck

Video: https://www.youtube.com/watch?v=mJqFI7vhqdA Blog post: https://explosion.ai/blog/applied-nlp-thinking Working on natural language processing for real-world applications requires more than just developing model implementations and evaluating them on existing datasets, or memorizing various library APIs. Often, what’s needed is an entirely different mindset: How can I break down complex business problems into machine learning components? How do I design my data to make the problem easier and get human experts involved? And how do I incorporate linguistic insights to find approaches that are more likely to succeed? In this talk, I’ll share some lessons we’ve learned from commercial use cases of our software, spaCy

March 29, 2025

ikayaniaamirshahzad@gmail.com

Run ComfyUI workflows for free with Gradio on Hugging Face Spaces

Index: Intro In this tutorial I will present a step-by-step guide on how to convert a complex ComfyUI workflow to a simple Gradio application, and how to deploy this application on Hugging Face Spaces ZeroGPU serverless structure, which allows for it to be deployed and run for free in a serverless manner. In this tutorial, we are going to work with Nathan Shipley’s Flux[dev] Redux + Flux[dev] Depth ComfyUI workflow, but you can follow the tutorial with any workflow that you would like. The tl;dr summary of what we will cover in this tutorial is: Export your ComfyUI workflow using

March 29, 2025

ikayaniaamirshahzad@gmail.com

Accelerating SD Turbo and SDXL Turbo Inference with ONNX Runtime and Olive

SD Turbo and SDXL Turbo are two fast generative text-to-image models capable of generating viable images in as little as one step, a significant improvement over the 30+ steps often required with previous Stable Diffusion models. SD Turbo is a distilled version of Stable Diffusion 2.1, and SDXL Turbo is a distilled version of SDXL 1.0. We’ve previously shown how to accelerate Stable Diffusion inference with ONNX Runtime. Not only does ONNX Runtime provide performance benefits when used with SD Turbo and SDXL Turbo, but it also makes the models accessible in languages other than Python, like C# and Java.

March 29, 2025

ikayaniaamirshahzad@gmail.com

Rust Performance Boost: Building Efficient Caching Systems From Scratch

As a best-selling author, I invite you to explore my books on Amazon. Don’t forget to follow me on Medium and show your support. Thank you! Your support means the world! Caching is one of the most powerful optimization techniques in software development. It’s a strategy I’ve employed countless times to boost application performance by storing computed results for future use. When implementing caching systems, Rust stands out as an exceptional language due to its performance characteristics and safety guarantees. I’ve found that Rust’s ownership model provides unique advantages when building cache implementations. The strict memory management ensures we don’t

March 29, 2025

ikayaniaamirshahzad@gmail.com

How to Translate Problems into Solutions · Explosion

We’ve been running Explosion for about five years now, which has given us a lot of insights into what Natural Language Processing looks like in industry contexts. In this blog post, I’m going to discuss some of the biggest challenges for applied NLP and translating business problems into machine learning solutions. About this post This blog post is based on talks I gave at the “Teaching NLP” workshop at NAACL 2021 and the L3-AI online conference. You can also watch the video here or view the slides. When you’re starting out in the field and are facing real problems to

March 29, 2025

ikayaniaamirshahzad@gmail.com

Preference Tuning LLMs with Direct Preference Optimization Methods

Addendum After consulting with the authors of the IPO paper, we discovered that the implementation of IPO in TRL was incorrect; in particular, the loss over the log-likelihoods of the completions needs to be averaged instead of summed. We have added a fix in this PR and re-run the experiments. The results are now consistent with the paper, with IPO on par with DPO and performing better than KTO in the paired preference setting. We have updated the post to reflect these new results. TL;DR We evaluate three promising methods to align language models without reinforcement learning (or preference tuning)