Holotron-12B – High Throughput Computer Use Agent

We’re thrilled to release Holotron-12B, a multimodal computer-use model from H Company. Post-trained from the open NVIDIA Nemotron-Nano-2 VL model on H Company’s proprietary data mixture, Holotron-12B is the result of a close collaboration between our research labs to engineer a new type of model optimized primarily for scale and performance in production. H Company is part of the NVIDIA Inception Program. The model is now available on Hugging Face. Most multimodal models today optimize primarily for static vision or […]

Read more

State of Open Source on Hugging Face: Spring 2026

This post examines how the open source AI landscape has shifted across competition, geography, technical trends, and emerging communities over the past year. We primarily examine community activity on Hugging Face across many types of metrics to give a holistic view of the ecosystem.  This post builds on an earlier analysis conducted mid-2025, available here, which examined what the Hugging Face Community is building. We recommend reading additional perspectives on the open source ecosystem in and outside of Hugging Face […]

Read more

What’s New in Mellea 0.4.0 + Granite Libraries Release

We have released Mellea 0.4.0 alongside three Granite Libraries: granitelib-rag-r1.0,granitelib-core-r1.0,granitelib-guardian-r1.0. Together, these releases make it easier to build structured, verifiable, and safety-aware AI workflows on top of IBM Granite models. Mellea is an open-source Python library for writing generative programs — replacing probabilistic prompt behavior with structured, maintainable AI workflows. Unlike general-purpose orchestration frameworks, Mellea is designed to make LLM-based programs maintainable and predictable through constrained decoding, structured repair loops, and composable pipelines (New to Mellea? Start with our introductory […]

Read more

Build a Domain-Specific Embedding Model in Under a Day

If you are building a RAG (Retrieval-Augmented Generation) system, you have likely hit this wall: Everything works… until it doesn’t. General-purpose embedding models are trained to understand the internet; not your contracts, manufacturing logs, proprietary chemical formulations or internal taxonomy. They capture broad semantic similarity, but they do not understand the fine-grained distinctions that matter in your domain. Fine-tuning an embedding model can improve the performance of your retrieval pipeline when off-the-shelf models fail to effectively capture domain-specific nuances. Despite […]

Read more

Quiz: Python Decorators 101

Interactive Quiz ⋅ 8 QuestionsBy Joseph Peart Share In this quiz, you’ll test your understanding of Python Decorators 101. Work through this quiz to review first-class functions, inner functions, and decorators, and learn how to create, reuse, and apply them to extend behavior cleanly in Python. The quiz contains 8 questions and there is no time limit. You’ll get 1 point for each correct answer. At the end of the quiz, you’ll receive a total score. The maximum score is […]

Read more

Quiz: How to Add Python to PATH

Interactive Quiz ⋅ 6 QuestionsBy Joseph Peart Share In this quiz, you’ll test your understanding of Add Python to PATH. By working through this quiz, you’ll review what the PATH environment variable is, how the shell searches it in order. You’ll also practice adding Python to PATH on Windows, Linux, and macOS, prepending directories with export, refreshing your session with source, and managing unwanted entries so the python command works as expected. The quiz contains 6 questions and there is […]

Read more

Quiz: Exploring Basic Data Types in Python

Interactive Quiz ⋅ 12 QuestionsBy Joseph Peart Share In this quiz, you’ll test your understanding of Python Data Types. By working through this quiz, you’ll revisit basic numeric, string, and Boolean types, how Python represents these objects, and common built-in functions. This quiz helps beginners solidify a foundation for working with Python types and using built-in functions in real programs. Work through the questions to check your skills and identify topics to review. The quiz contains 12 questions and there […]

Read more

Build Your Weekly Python Study Schedule: 7 Days to Consistent Progress

Staying consistent with learning Python can be challenging. This guide helps you create a weekly Python study schedule that you can stick to and shows you how it works in practice. By the end of this guide, you’ll have a practical, personal schedule that fits your life, not the other way around. You’ll walk away with a repeatable 7-day plan and a worksheet you can reuse each week. You’ll know exactly what to study, when to study, and how to […]

Read more

Quiz: Linked Lists in Python: An Introduction

Interactive Quiz ⋅ 9 QuestionsBy Joseph Peart Share In this quiz, you’ll test your understanding of Linked Lists in Python. By working through this quiz, you’ll revisit what linked lists are, when to use collections.deque, how to implement your own linked lists, and the other linked list types and use cases. The quiz contains 9 questions and there is no time limit. You’ll get 1 point for each correct answer. At the end of the quiz, you’ll receive a total […]

Read more

Downloading Files From URLs With Python

Python makes it straightforward to download files from a URL with its robust set of libraries. For quick tasks, you can use the built-in urllib module or the requests library to fetch and save files. When working with large files, streaming data in chunks can help save memory and improve performance. You can also perform parallel file downloads using ThreadPoolExecutor for multithreading or the aiohttp library for asynchronous tasks. These approaches allow you to handle multiple downloads concurrently, significantly reducing […]

Read more
1 2 3 1,067