"Attention is all you need" implementation from scratch in PyTorch. A Twitter thread: 1/

Thrilled to present my latest blog post: "Demystifying Document Question-Answering Chatbot - A Comprehensive Step-by-Step Tutorial with LangChain" 🔗: amaarora.github.io/posts/2023-07-… It's the most exhaustive resource that you'll find on the topic going into depths of LangChain. 1/

The most detailed and practical write up on applying LLMs! 🙏 This reads like a survey paper but written for the industry and applications Eugene Yan is known as the best NLP writer for a reason. It’s the most comprehensive overview of patterns on building Large Language Models

Built a notebook that makes it dumb simple to fine-tune LLaMA 2. Just load in a dataset, and run it! colab.research.google.com/drive/1Zmaceu6…

Great series of articles explaining gradient boosting by Terence Parr and Jeremy Howard explained.ai/gradient-boost…

One major way to improve your RAG system is to fine-tune your embedding model ⚙️ We’ve created a full repo/guide (Simon Suo) on fine-tuning embeddings over any unstructured text (no labels needed) 🌟 5-10% improvement 📈 in evals + runs on your MacBook! github.com/run-llama/fine…

💬 Chat your way to data insights! Learn from Amjad Raza (Ph.D) how to converse with pandas DataFrames by building an app using and OpenAI API, and Docker for local or cloud deployments. 🐼 💻 Demo: buff.ly/44tBawF 📖 Read more: buff.ly/45wNyNJ

Forgive me, for I am about to Bayes. Lesson: Don't trust intuition, for even simple prior+likelihood scenarios defy it. Four examples below, each producing radically different posteriors. Can you guess what each does? Revealed in next tweet >>

Temporian is a new Google and Tryolabs open-source #timeseries Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖 🚀🚀🚀🚀🚀 According to devs 'Temporian is purpose-built for mastering temporal data challenges

Big if true, academic lab at NYU claim they have created zero shot large scale model for #timeseries #forecasting. As I have mentioned a few weeks ago, we are going to see a deluge of time series LLM models over the next weeks and months. The key question is what these models

My new course, Generative AI for Everyone, is now available! Learn how Generative AI works, how to use it in professional or personal settings, and how it will affect jobs, businesses and society. This course is accessible to everyone, and assumes no prior coding or AI

Data-Driven Optimization: Enhancing Combinatorial Optimization Solvers with Machine Learning #optimization #Machinelearning #analytics [Analytics] bit.ly/3MzxnrB

🚀🎉 Excited to announce 🌟 PyTorch Frame 🌟 - our new open-source initiative in PyTorch! Dive into multi-modal tabular deep learning like never before! Link: github.com/pyg-team/pytor… #PyTorch #OpenSource (1/6)

🧑‍🔬👷 The LLM Course is now complete! I added the LLM Engineer Roadmap, a list of high-quality resources to build LLM-powered applications and deploy them. 💻 LLM Course: github.com/mlabonne/llm-c…

Our #Logistics #Algorithms team is excited to share their research paper, describing the optimisation problem of order batching and picking in our warehouses. Check the blog post for a short introduction and links to the validation code: zln.do/4bNn8e5 #ZalandoTech

Inspired by this tweet, I built my own locally running typing assistant with Ollama and Mistral 7B. It only took ~100 lines of Python code and works really well! I also created a video with step-by-step explanations: - Code: github.com/patrickloeber/… - Blog post:

I want to show you a clever trick you didn't know before. Imagine you have six months' worth of data. You want to build a model, so you take the first five months to train it. Then, you use the last month to test it. This is a common approach for building machine learning

When there is sufficient data, open source time series LLMs (LTSM) can’t outperform naive models and simple statistical ensembles. Some people argue that they “become useful” when there is “scarce data”, but what actually happens in such cases is that time series LLMs

My full, 1-hour tutorial on how to build a RAG application from scratch. Python + + OpenAI

The trouble with uncertainty quantification in ML is a lack of guarantee: prediction intervals that are too short and class probabilities are miscalibrated. A solution: conformal prediction. To get started, I wrote a beginner-friendly, hands-on book.