huggingface

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

Sentence Transformers is a Python library for using and training embedding and reranker models for applications like retrieval augmented generation, semantic search, and more. In my previous blogpost, I introduced the new multimodal capabilities, showing how to use embedding and reranker models that handle text, images, audio, and video. In this blogpost, I’ll show you how to train or finetune these multimodal models on your own data. As a practical example, I’ll walk through finetuning Qwen/Qwen3-VL-Embedding-2B for Visual Document Retrieval […]

Read more
huggingface

The PR you would have opened yourself

Making transformers models available in mlx-lm using a Skill and test harness TL;DR We provide a Skill and a test harness to help port language models from transformers to mlx-lm, so they become (almost) instantly available the moment they are added to transformers. The Skill is designed to support contributors and reviewers as an aide, not an automation. We explain why we did it, how, and comment about how to meaningfully contribute to open source in the age of agents. […]

Read more
huggingface

Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents

TL;DR — We extend the RLVE framework from single-turn reasoning puzzles to multi-turn, tool-augmented e-commerce conversations. EcomRLVE-GYM provides 8 verifiable environments — product discovery, substitution, cart building, returns, order tracking, policy QA, bundle planning, and multi-intent journeys — each with procedural problem generation, a 12-axis difficulty curriculum, and algorithmically verifiable rewards. We train a Qwen 3 8B model with DAPO over 300 steps and present early results demonstrating that environment scaling and adaptive difficulty transfer to agentic, real-world task completion. […]

Read more
huggingface

Building a Fast Multilingual OCR Model with Synthetic Data

Training a high-quality OCR model requires a large quantity of annotated image-text pairs: images with precise bounding boxes, transcriptions, and ideally reading order information at the word, line, and paragraph level. Every approach to curating this data comes with tradeoffs. Existing benchmark datasets like ICDAR and Total-Text have clean labels but limited scale, typically tens of thousands of images skewed toward English and Chinese. Manual annotation produces the highest quality labels but is expensive and slow, making it impractical at […]

Read more
Python

Quiz: Working With Python Virtual Environments

Interactive Quiz ⋅ 6 QuestionsBy Joseph Peart Share Test your understanding of the Working With Python Virtual Environments video course. You’ll revisit why virtual environments matter, how to create and activate them, and how to install and manage packages inside an isolated Python environment. The quiz contains 6 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 100%. Good […]

Read more
Python

Learning Path: Python Game Development

Learning Path ⋅ Skills: Turtle, Rich, PySimpleGUI, Tkinter, Pygame, Arcade Python game development is one of the most fun ways to put your programming skills into practice. This learning path takes you from simple command-line games to full 2D graphical games with sprites, collision detection, and animation. By completing this path, you’ll be able to:    

Read more
Python

Quiz: Welcome to Real Python!

Interactive Quiz ⋅ 10 QuestionsBy Joseph Peart Share In this quiz, you’ll test your understanding of Welcome to Real Python! By working through this quiz, you’ll revisit key platform features like video courses, written tutorials, interactive quizzes, Learning Paths, and the Slack community. You’ll also review strategies for learning effectively, including immersion, daily progress, and building a habit. The quiz contains 10 questions and there is no time limit. You’ll get 1 point for each correct answer. At the end […]

Read more
Python

Quiz: Design and Guidance: Object-Oriented Programming in Python

Interactive Quiz ⋅ 7 QuestionsBy Joseph Peart Share Test your understanding of the Design and Guidance: Object-Oriented Programming in Python video course. You’ll revisit single responsibility, open-closed, Liskov substitution, interface segregation, and dependency inversion. You’ll also review when to use classes in Python and alternatives to inheritance like composition and dependency injection. The quiz contains 7 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 […]

Read more
Python

Learning Path: Python Data Structures

Learning Path ⋅ Skills: Python, Strings, Lists, Tuples, Dictionaries, Sets, List Comprehensions, range(), Bytes, Sorting You will learn how to work with Python’s core built-in data structures, including strings, lists, tuples, dictionaries, sets, bytes, and bytearrays. This path covers string operations, list comprehensions, shallow and deep copying, sorting with sorted() and .sort(), and the range() function. You will also    

Read more
Python

Learning Path: Python Control Flow and Loops

Learning Path ⋅ Skills: Python, Control Flow, Conditional Statements, Booleans, for Loops, while Loops, enumerate, Nested Loops, break, continue, pass In this learning path, you’ll learn about Python’s control flow tools. Starting with conditional statements and Boolean operators, you’ll move on to for and while loops, enumerate(), nested loops, and loop control keywords like break, continue, and pass. Share

Read more
1 2 3 4 … 1,031