Articles for category: AI Tools

March 30, 2025

ikayaniaamirshahzad@gmail.com

Changelog · Prodigy · An annotation tool for AI, Machine Learning & NLP

Select page…Get Started › Prodigy 101Get Started › Installation & SetupGet Started › ChangelogUsage › Named Entity RecognitionUsage › Span CategorizationUsage › Text ClassificationUsage › Dependencies & RelationsUsage › Computer VisionUsage › Audio & VideoUsage › Task RoutingUsage › Large Language ModelsUsage › ReviewUsage › Custom RecipesUsage › Custom InterfacesUsage › MetricsUsage › DeploymentAPI › RecipesAPI › Annotation InterfacesAPI › Web ApplicationAPI › Loaders & Input DataAPI › Components & FunctionsAPI › DatabasePlugins › Open Source PluginsPlugins › Single Sign-onPlugins › Modal This page lists the history of changes to Prodigy. Whenever a new update is available, you’ll receive an

March 30, 2025

ikayaniaamirshahzad@gmail.com

SafeCoder vs. Closed-source Code Assistants

For decades, software developers have designed methodologies, processes, and tools that help them improve code quality and increase productivity. For instance, agile, test-driven development, code reviews, and CI/CD are now staples in the software industry. In “How Google Tests Software” (Addison-Wesley, 2012), Google reports that fixing a bug during system tests – the final testing stage – is 1000x more expensive than fixing it at the unit testing stage. This puts much pressure on developers – the first link in the chain – to write quality code from the get-go. For all the hype surrounding generative AI, code generation seems

March 30, 2025

ikayaniaamirshahzad@gmail.com

[Boost] – DEV Community

Thank you to our Diamond Sponsor Neon for supporting our community. DEV Community — A constructive and inclusive social network for software developers. With you every step of your journey. Home Tags About Contact Code of Conduct Privacy Policy Terms of use Source link

March 30, 2025

ikayaniaamirshahzad@gmail.com

Our Year in Review · Explosion

As 2019 draws to a close and we step into the 2020s, we thought we’d take a look back at the year and all we’ve accomplished. And we realized we had so much that we could give you a month-by-month rundown of everything that happened. We’re also very happy to see our team grow this year, with four new members working under the Explosion umbrella: Sofie Van Landeghem, Adriane Boyd, Walter Henry and Sebastián Ramírez. 📻 Jan 15: The year started out with us as guests on the NLP Highlights podcast, hosted by Matt Gardner and Waleed Ammar of Allen

March 30, 2025

ikayaniaamirshahzad@gmail.com

Overview of natively supported quantization schemes in 🤗 Transformers

We aim to give a clear overview of the pros and cons of each quantization scheme supported in transformers to help you decide which one you should go for. Currently, quantizing models are used for two main purposes: Running inference of a large model on a smaller device Fine-tune adapters on top of quantized models So far, two integration efforts have been made and are natively supported in transformers : bitsandbytes and auto-gptq. Note that some additional quantization schemes are also supported in the 🤗 optimum library, but this is out of scope for this blogpost. To learn more about

March 30, 2025

ikayaniaamirshahzad@gmail.com

Building a Team That Resembles Your Brand Values and Vision

“Your Brand is Only as Strong as the Team Behind It” When Steve Jobs founded Apple, he did not just hire personnel—he built a movement. The personnel who walked in with him were not just qualified professionals but those who embarked on his mission of innovation, simplicity, and design excellence. And what came out of that? A brand that changed the world. If you want to create a brand that stands the test of time, you need a team who completely understands and shares your core values and vision. But how do you ensure that your team doesn’t just understand

March 30, 2025

ikayaniaamirshahzad@gmail.com

Fine-tuning Llama 2 70B using PyTorch FSDP

In this blog post, we will look at how to fine-tune Llama 2 70B using PyTorch FSDP and related best practices. We will be leveraging Hugging Face Transformers, Accelerate and TRL. We will also learn how to use Accelerate with SLURM. Fully Sharded Data Parallelism (FSDP) is a paradigm in which the optimizer states, gradients and parameters are sharded across devices. During the forward pass, each FSDP unit performs an all-gather operation to get the complete weights, computation is performed followed by discarding the shards from other devices. After the forward pass, the loss is computed followed by the backward

March 30, 2025

ikayaniaamirshahzad@gmail.com

Java Multithreading Explained: Concepts, Examples, and Best Practices

Multithreading is an essential concept in Java that allows multiple threads to run concurrently, making applications more efficient and responsive. In this blog, we will explore Understanding Multithreading in Java, its benefits, real-world applications, and best practices to follow when developing multithreaded programs. What is Multithreading in Java? Multithreading is the ability of a Java program to execute multiple threads simultaneously. A thread is a lightweight sub-process that shares the same memory space with other threads within a process. The Java Virtual Machine (JVM) supports multithreading, making Java a powerful language for developing applications that require parallel execution. Threads help