GitHub Trends

#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#aiagent#chatgpt#finance#fingpt#large_language_models#multimodal_deep_learning#prompt_engineering#robo_advisor FinRobot is a free open-source platform using AI agents and large language models for easy financial analysis. It automates stock predictions, equity reports from 10-K filings, risk checks, valuations like P/E ratios, and trading strategies with real-time data from news and markets. Install via Python, add API keys, and run demos for instant insights. This saves you hours on complex research, delivers pro-level reports and forecasts accurately, and helps make smarter investment decisions without expert skills. https://github.com/AI4Finance-Foundation/FinRobot

#jupyter_notebook#chinese_llm#chinese_nlp#finetune#generative_ai#instruct_gpt#instruction_set#llama#llm#lora#open_models#open_source#open_source_models#qlora AirLLM is a tool that lets you run very large AI models on computers with limited memory by using a smart layer-by-layer loading technique instead of traditional compression methods. You can run a 70-billion-parameter model on just 4GB of GPU memory, or even a 405-billion-parameter model on 8GB, without losing model quality. The benefit is that you can use powerful AI models on affordable hardware without expensive upgrades, and the tool also offers optional compression features that can speed up performance by up to 3 times while maintaining accuracy. https://github.com/lyogavin/airllm

#jupyter_notebook#agent#agentic_ai#agents#authentication#bedrock#core#gateway#identity_management#memory_management#production_code#runtime Amazon Bedrock AgentCore lets you build, deploy, and run AI agents securely at scale with any framework like CrewAI or LangGraph and any model, without managing complex infrastructure. It offers serverless runtime for long tasks up to 8 hours, gateway to connect tools like Slack or APIs easily, memory for personalized experiences, identity management, built-in code interpreter and browser tools, plus observability. This saves time by skipping heavy setup, speeds prototypes to production, cuts costs with pay-per-use, and boosts security—helping you create powerful agents faster for real business needs. https://github.com/awslabs/amazon-bedrock-agentcore-samples

#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#chirp#gemini#google_cloud#imagen#lyria#nano_banana#veo#vertex_ai GenMedia Creative Studio is a web app that lets you use Google Cloud’s generative AI tools to create images, videos, music, and speech. It includes features like Imagen for images, Veo for videos, Lyria for music, and Chirp for speech, plus creative workflows for tasks like virtual try-ons and moodboards. You can experiment with these tools to quickly make and test creative media, helping you bring new ideas to life faster and more easily. https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio

#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

#jupyter_notebook#chatgpt#finance#fingpt#fintech#large_language_models#machine_learning#nlp#prompt_engineering#pytorch#reinforcement_learning#robo_advisor#sentiment_analysis#technical_analysis FinGPT is an open-source AI tool designed specifically for finance, helping you analyze financial news, predict stock prices, and get personalized investment advice quickly and affordably. Unlike costly models like BloombergGPT, FinGPT can be updated frequently with new data at a low cost, making it more accessible and timely. It uses advanced techniques like reinforcement learning from human feedback to tailor advice to your preferences, such as risk tolerance. You can use FinGPT for tasks like sentiment analysis, robo-advising, fraud detection, and portfolio optimization, helping you make smarter financial decisions with up-to-date insights. https://github.com/AI4Finance-Foundation/FinGPT

#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#darknet#pytorch#scaled_yolov4#yolor#yolov3#yolov4#yolov7 YOLOv7 is a powerful tool for detecting objects in images and videos. It is fast, accurate, and can work well on devices with limited power, making it useful for real-time applications like self-driving cars and surveillance systems. YOLOv7 uses advanced techniques like Feature Pyramid Networks to detect objects of different sizes and can handle complex scenes with overlapping objects. This makes it beneficial for users who need quick and precise object detection in various environments. https://github.com/WongKinYiu/yolov7