Carlos Daniel Jimenez’s Post

Built a little tool called GoDistribute! 🎉 It's a simple way to run distributed tasks across multiple nodes without messing around with Kubernetes or any other complex system. I needed it to train thousands of machine learning models in dozens of nodes. Example: seq 10 | ./GoDistribute run --command "bash -c 'echo {}'" --config nodes.yaml --jobs-per-node 2 --image-tar /tmp/ubuntu2204.tar Check it out on GitHub: https://buff.ly/4eE7jHA 🙌"

"If you’ve never productionised a model before (or if you don’t know what that sentence even means), this guide is for you." Deploy a LightGBM ML Model With GitHub Actions by Matt Chapman

DREAM - a Distributed RAG Experimentation Framework 🧑🔬 Building RAG comes with a lot of knobs that you need to tune, and it’s important that you setup the right experimentation infrastructure to build production RAG. This project by Aishwarya Prabhat provides a comprehensive full-stack blueprint for letting you run experimentation and evals in a distributed manner to pick the combination that works best. Uses the following architecture:  ✅ Ray (Anyscale) - distributed compute ✅ LlamaIndex - advanced RAG techniques ✅ Ragas (Shahul ES) - synthetic data + evals!  ✅ MinIO - store data + artifacts ✅ MLflow - experiment tracking ✅ Project Jupyter - interactive experimentation against Ray ✅ ArgoCD - deploying tooling to k8s cluster There’s sample code so you can follow along yourself - check It out! Full post here: https://lnkd.in/gVtHx_TQ Github project: https://lnkd.in/gYvas-hE

These are absolutely wonderful developments for a production-level RAG. One of the main issues with RAG systems is RAG tuning and scalability. These are the first few steps in the right direction. Information in production behaves and costs a lot differently than in an experiment! #RAG #Production #LLaMAindex #Langchain

Just completed the second week of MLOps Zoomcamp. The lessons covered include: 1. Experiment Tracking Intro. 2. Getting Started with MLflow. 3. Experiment Tracking with MLflow. 4. Model Management. 5. Model Registry. 6. MLflow in Practice. 7. MLflow Benefits Limitations and Alternatives. The link to the course is below: https://lnkd.in/dy5Md3WN

Continued developing my skills in Snowflake today by completing the Quickstart, "Tasty Bytes - RAG Chatbot Using Cortex and Streamlit". What I Learned: - How to build a chatbot using Cortex LLMs - How to build a Streamlit in Snowflake application - Basics of retrieval augmented generation (RAG) Highly recommend trying this Quickstart if you wish to learn Cortex LLM Functions!

Sharpening my skills in Calculus - I for Machine Learning! Functions • Continuous & Discontinuous Functions • Approaching Infinity Derivatives • Delta Method • Derivative Notation • Constants • Power Rule • Constant Product Rule • Sum Rule Differentiation Rules • Product Rule • Quotient Rule • Chain Rule Automatic Differentiation • Autodiff with PyTorch • Autodiff with TensorFlow Explore my Jupyter Notebook on GitHub: https://lnkd.in/g2UPS_jm #calculusForML #machinelearning #github #mathematics #datascience #problem-solving #continuouslearning"

using Usupervised ML Check out the Code on GitHub: [https://lnkd.in/eAAK7G6U]

Get ready to level up your MLOps skills! In this live workshop session, we'll dive into crafting modular code for your machine learning projects. Learn how to build reusable components, streamline your development process, and make your ML systems more maintainable and scalable. Session Recording and Source code available at: https://lnkd.in/gtHcseix What You'll Do: Master the principles of modular code design for ML projects. Build and integrate modular components into a real-world ML pipeline. Get expert tips on effective code organization and refactoring.

Day 32 of #100DaysOfMachineLearning Today, I implemented Logistic Regression from scratch. This hands-on approach helped me gain a thorough understanding of the algorithm's fundamentals and its application in binary classification problems. Looking forward to leveraging this knowledge in future projects! GitHub:https://lnkd.in/ebHymcp5 #MachineLearning #DataScience #LogisticRegression #FromScratch #LearningJourney #ML