Mamba: The Hard Way

A post about Mamba, a recent neural architecture that can be roughly thought of as a modern recurrent neural network (RNN). The model works really well and is a legitimate competitor with the ubiquitous Transformer architecture. It has gotten a lot of attention.

https://srush.github.io/annotated-mamba/hard.html

Build a Retrieval-Augmented Generation Chatbot in 5 Minutes

In under 5 minutes and with only 100 lines of Python code, Rohan Rao, senior solutions architect at NVIDIA, demos how large language models (LLMs) can be developed and deployed for AI chatbot applications—without needing your own GPU infrastructure.

https://www.youtube.com/watch?v=N_OOfkEWcOk

X-PLUG / MobileAgent

Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

https://github.com/X-PLUG/MobileAgent

Generative AI Full Course – Gemini Pro, OpenAI, Llama, Langchain, Pinecone, Vector Databases & More

Learn about generative models and different frameworks, investigating the production of text and visual material produced by artificial intelligence.

https://www.youtube.com/watch?v=mEsleV16qdo

Sensei

Generate Synthetic Data Using OpenAI or MistralAI.

https://github.com/migtissera/Sensei

Advanced Web Scraping With Python: Extract Data From Any Site

This article covers how to get and manage cookies and custom headers, avoid TLS fingerprinting, recognize important HTTP headers to send in requests, and how to implement exponential-backoff HTTP request retrying.

https://jacobpadilla.com/articles/advanced-web-scraping-techniques

gemma_pytorch

The official PyTorch implementation of Google's Gemma models.

https://github.com/google/gemma_pytorch

GPT Pilot – what we learned in 6 months of working on a CodeGen pair programmer

The article discusses the learnings from six months of working on a CodeGen pair programmer, GPT Pilot, aiming to have human developers understand the codebase and provide detailed explanations of added code to facilitate collaboration between human developers and AI in coding tasks

https://blog.pythagora.ai/2024/02/19/gpt-pilot-what-did-we-learn-in-6-months-of-working-on-a-codegen-pair-programmer/

Deploy Mistral Large to Azure and create a conversation with Python and LangChain

Step-by-step guide to deploying Mistral Large to Azure.

https://neon.tech/blog/deploy-mistral-large-to-azure-and-chat-with-langchain

hotpdf

hotpdf is a fast PDF parsing library to extract text and find text within PDF documents built on top of pdfminer.six

https://github.com/weareprestatech/hotpdf

allenai / OLMo

Modeling, training, eval, and inference code for OLMo

https://github.com/allenai/OLMo

Dependency Injection Explained in 7 Minutes

This video explains why dependency injection is a game-changer for your coding projects. Creating loosely coupled code is key to making the code more flexible and more maintainable. This is all possible through the implicit use of dependencies.

https://www.youtube.com/watch?v=DpMGEhwuuyA

ok-robot

An open, modular framework for zero-shot, language conditioned pick-and-drop tasks in arbitrary homes.

https://github.com/ok-robot/ok-robot

Graphinate. Data to Graphs.

Graphinate is a python library that aims to simplify the generation of Graph Data Structures from Data Sources.

https://github.com/erivlis/graphinate