Find similar content

#jupyter_notebook This free tutorial series teaches hands-on large model skills like fine-tuning, prompting, math reasoning, jailbreaks, agents, and safety alignment, with slides, guides, code notebooks, and new Huawei Ascend courses (PPTs, videos) for full development workflows. You'll quickly master AI models through simple practices, boosting your course projects, research, or career in large language models. https://github.com/Lordog/dive-into-llms

#jupyter_notebook Insanely Fast Whisper is a simple CLI tool that transcribes audio files super quickly on your NVIDIA GPU or Mac using OpenAI's Whisper Large v3 model with optimizations like Flash Attention 2. Install via `pipx install insanely-fast-whisper` and run `insanely-fast-whisper --file-name youraudio.mp3 --flash True` to transcribe 150 minutes of audio in under 98 seconds. You benefit by saving hours on tasks like podcasting or meetings, getting accurate text output fast without cloud costs or slow processing. https://github.com/Vaibhavs10/insanely-fast-whisper

#jupyter_notebook DINOv3 offers powerful self-supervised vision models from Meta AI, like ViT up to 7B parameters and ConvNeXt, pretrained on 1.7B web or satellite images. Load them easily via PyTorch Hub, Hugging Face Transformers (v4.56+), or timm (v1.0.20+), with code examples for features, depth, detection, and segmentation. You benefit by using these top-performing, dense features without fine-tuning or labels—saving time and compute for tasks like classification, object detection, and zero-shot analysis on your images. https://github.com/facebookresearch/dinov3

#jupyter_notebook Retrieval Augmented Generation (RAG) helps large language models (LLMs) answer questions using up-to-date or private information by connecting them to external data sources, unlike fine-tuning which retrains the model on specific data. RAG is useful when you need current, dynamic information without costly retraining, making it ideal for tasks like customer support or knowledge management. Fine-tuning is better for deep expertise in a specialized field but requires more data and effort. Using RAG lets you get accurate, relevant answers quickly by combining the model’s language skills with fresh, specific data, improving usefulness and reliability. https://github.com/langchain-ai/rag-from-scratch

#jupyter_notebook SAM 2 is a powerful new AI model that can quickly and accurately separate objects in both images and videos, even if it has never seen them before. It works in real-time, allowing you to select objects with simple prompts like clicks or boxes and refine the results interactively. This makes tasks like video editing, object tracking, and image annotation much easier and faster. SAM 2’s ability to handle complex scenes and track objects smoothly across video frames helps improve creativity and productivity in many fields, from media production to computer vision research. It is open-source and easy to use with Python and PyTorch. https://github.com/facebookresearch/segment-anything

#jupyter_notebook This course guides you through building and deploying your own AI agents using popular tools like OpenAI Agents SDK, CrewAI, LangGraph, AutoGen, and MCP over six weeks. You’ll learn to create agents that can think, act, and work together, with clear setup instructions for Windows, Mac, and Linux, plus support if you get stuck. The benefit is that you gain hands-on experience in the latest AI agent technology, making you ready to develop smart, autonomous systems for real-world tasks, while also connecting with a helpful community and having fun along the way[1][2][3]. https://github.com/ed-donner/agents

#jupyter_notebook MiniCPM is a family of highly efficient, open-source AI models designed to run well even on regular computers or mobile devices, not just powerful servers. The latest version, MiniCPM 4, is especially fast and smart, handling long texts and complex tasks much quicker than similar models, and it can be used for things like answering questions, writing summaries, and working with tools or data. MiniCPM also supports both English and Chinese, making it useful for bilingual users. The main benefit is that you get strong AI performance without needing expensive hardware, so it’s easy to use for many different applications[1][5]. https://github.com/OpenBMB/MiniCPM

#jupyter_notebook Unsloth is a tool that makes it much faster and easier to fine-tune large language models like Llama, Mistral, and Gemma, even on regular computers or single GPUs. It uses smart tricks to speed up training by 2 to 5 times and cuts memory use by up to 70%, so you can train models quickly without needing expensive hardware[1][3][4]. The benefit is that anyone—developers, researchers, or AI fans—can create custom AI models for different tasks, from chatting to vision, in less time and with less hassle, using ready-made notebooks and guides for popular models[3][5]. https://github.com/unslothai/notebooks

#jupyter_notebook Learning about Large Language Models (LLMs) can be very beneficial. You can build exciting projects over eight weeks, starting with simple tasks and moving to more complex ones. This journey helps you develop deep expertise in AI and LLMs. You'll learn by doing hands-on projects, which is a fun and effective way to understand how these models work. By the end, you'll have skills that can be used in real-world applications, making it a valuable learning experience. https://github.com/ed-donner/llm_engineering

#jupyter_notebook DINOv2 is a powerful AI model from Meta AI that learns to understand images without needing labeled data, using self-supervised learning. It was trained on 142 million images and creates strong visual features that work well for many tasks like image classification, depth estimation, and segmentation without extra fine-tuning. You can use its pretrained models easily with simple classifiers, saving time and effort. DINOv2 is efficient, scalable, and performs better than many other models, making it great for building versatile computer vision applications quickly and accurately. It’s open-source and ready to use with PyTorch. https://github.com/facebookresearch/dinov2

#jupyter_notebook#jax Flax is a library for creating neural networks with JAX. It offers a flexible way to build and analyze these networks. The new Flax NNX API makes it easier to work with neural networks by using regular Python objects, which helps in creating, debugging, and analyzing models more efficiently. This means users can express their models in a more intuitive way, making it simpler to develop and modify neural networks. Flax also provides many tools and examples to help users get started quickly. https://github.com/google/flax

#jupyter_notebook#deep_learning#pytorch You can learn PyTorch effectively in 20 days with a friendly, well-structured guide designed for those who already know some machine learning basics and have used Keras, TensorFlow, or PyTorch before. The book breaks down PyTorch concepts from easy to hard, with clear examples and practical code you can use right away. It includes a daily plan requiring 30 minutes to 2 hours, covering modeling, core concepts, APIs, and even advanced topics like GPU training and recommendation systems. This approach makes mastering PyTorch easier and faster, helping you build strong skills for deep learning projects and real applications. https://github.com/lyhue1991/eat_pytorch_in_20_days