Alejandro Saucedo’s Post

Sebastian Raschka has dropped a 3-hour workshop on building LLMs from the Ground Up! This resource comes with great timing as LLMs continue to grow in popularity, covering the foundations across input data preparation, model architecture coding, pretraining, and fine-tuning. This is quite comprehensive as it dives into practical coding examples using PyTorch and LitGPT, building the core fundamentals from scratch and training simplified LLM versions like GPT-2. Video and summary: https://lnkd.in/gyEvwh9n -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

Lessons brought together by a group of experts building production LLM products throughout the past year: Some of the key learnings include the importance of prompt engineering using structured outputs, employing deterministic workflows, and establishing robust evaluation and monitoring frameworks starting with inference APIs, avoiding unnecessary finetuning, focusing on domain-specific applications, and building LLMOps for faster iteration and product differentiation. This is a great set of best practices in prompting, Retrieval-Augmented Generation, workflow optimization, and evaluation relevant for development of LLM-powered apps. https://applied-llms.org/ -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

Stanford University has been publishing seminar videos on the frontier of machine learning systems, covering key concepts around challenges and solutions in AI research and industry in conversation with thought leaders in the space. This is quite a great video series as it features expert speakers from academia and industry, the series covers a wide range of topics including programming ML systems with frameworks like JAX, data labeling with tools like Snorkel, deploying robust models, hyperparameter optimization, and end-to-end ML pipelines. Video Playlists: https://lnkd.in/dwYhFPJ -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

Lessons brought together by a group of experts building production LLM products throughout the past year: Some of the key learnings include the importance of prompt engineering using structured outputs, employing deterministic workflows, and establishing robust evaluation and monitoring frameworks starting with inference APIs, avoiding unnecessary finetuning, focusing on domain-specific applications, and building LLMOps for faster iteration and product differentiation. This is a great set of best practices in prompting, Retrieval-Augmented Generation, workflow optimization, and evaluation relevant for development of LLM-powered apps. https://applied-llms.org/ -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

The many ways to deploy a machine learning model from the team at Outerbounds: A great overview for production ML practitioners on the diverse deployment strategies for ML/AI models, focusing on the critical considerations of scale, reliability, and iteration speed. It is often key to consider the broad range of technical requirements based on the application needs - i.e. batch vs real time, reusable vs specialized, modalities, etc. Great practical examples and conceptual frameworks to identify the most suitable deployment approach - check it out: https://lnkd.in/gjEtDZGM -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

The many ways to deploy a machine learning model from the team at Outerbounds: A great overview for production ML practitioners on the diverse deployment strategies for ML/AI models, focusing on the critical considerations of scale, reliability, and iteration speed. It is often key to consider the broad range of technical requirements based on the application needs - i.e. batch vs real time, reusable vs specialized, modalities, etc. Great practical examples and conceptual frameworks to identify the most suitable deployment approach - check it out: https://lnkd.in/eqJWadfr -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

As we celebrate our 300th newsletter we invite everyone to contribute to an exciting survey on the State of Production Machine Learning! We have designed the questions to provide meaningful insights on the current landscape of production ML in 2024. By participating, you'll contribute valuable information about the machine learning tools and platforms you use and your ML ecosystem. Your input will help create a comprehensive overview of common practices, tooling preferences, and challenges faced when deploying models to production, ultimately benefiting the entire ML community 🚀 Survey: https://lnkd.in/eb4udcDs -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

One of the best books on Bayesian Data Analysis is available for free, covering key fundamentals like probability and inference, single and multiparameter models, and hierarchical models. This is a great resource to go from basics to the more advanced nuances, such as computational techniques like Markov chain Monte Carlo and Hamiltonian Monte Carlo, as well as practical deep dives across other topics like regression models and nonparametric methods. Free Book: https://lnkd.in/eEfPff5P -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

Don't mock machine learning (in Unit Tests): A great piece by Eugene Yan which showcases the unique challenges ML practitioners face in unit testing ML code, different to traditional software development. In ML we face logic that may not be static nor deterministic, instead we face dynamic entities that learn from data. However to tackle these challenges, we can using simple data samples, testing against models with random or empty weights, and writing critical tests against actual models while avoiding testing external libraries. Another great resource from Eugene Yan providing practical advice for practitioners that accommodate the complexities of ML code and models. Deep dive: https://lnkd.in/dstHD4JW -- If you liked this article you can join 50,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata

One of the best books on Bayesian Data Analysis is available for free, covering key fundamentals like probability and inference, single and multiparameter models, and hierarchical models. This is a great resource to go from basics to the more advanced nuances, such as computational techniques like Markov chain Monte Carlo and Hamiltonian Monte Carlo, as well as practical deep dives across other topics like regression models and nonparametric methods. Free Book: https://lnkd.in/ebSVrSKv -- If you liked this article you can join 60,000 practitioners for weekly tutorials, resources, OSS frameworks, and MLOps events across the machine learning ecosystem: https://lnkd.in/eRBQzVcA #ML #MachineLearning #ArtificialIntelligence #AI #MLOps #AIOps #DataOps #augmentedintelligence #deeplearning #privacy #kubernetes #datascience #python #bigdata