Understanding Reasoning in LLMsThese notes are based on Sebastian’s article about Understanding Reasoning LLMs from his newsletter. It offers valuable insights explained…6d ago6d ago
Key Takeaways from the MLOps Data Lifecycle in Production CourseAs I revisit the Machine Learning Data Lifecycle in Production course (a refresher before diving into the third course), I’d like to share…Jan 15Jan 15
From Raw Data to Model Efficiency: Mastering Feature Engineering and SelectionIn the world of machine learning, your model is only as good as the data it learns from. Transforming raw data into a structured…Dec 6, 2024Dec 6, 2024
Enhancing Large Language Models: The Power of Continued Pre-Training𝐖𝐡𝐚𝐭 𝐢𝐬 𝐜𝐨𝐧𝐭𝐢𝐧𝐮𝐞𝐝 𝐩𝐫𝐞-𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠Nov 17, 2024Nov 17, 2024
Reproducing GPT-2 124M: Key Insights from Andrej Karpathy’s 4-Hour Deep DiveThis is a summary of Andrej karpathy’s video about pre-training a GPT-2 124M parameter model from scratch.Feel free to check it using this…Sep 10, 2024Sep 10, 2024
Multi-Agent System with Crew AI: A Short Course SummaryPlease note that this article contains direct quotes content from the short course on multi-agent systems with Crew AI.Jul 4, 2024Jul 4, 2024
Stanford’s CS25: Lecture 2summaryLecture 2 of Stanford University’s CS25 V4 Transformers course was delivered by Jason Wei and Hyung Won Chung. Highly recommended to watch…Jul 2, 2024Jul 2, 2024
Stanford’s CS25: Lecture 1 summaryI recently watched the first lecture of Stanford University CS25 V4 Transformers course, and presented by Div Garg, Steven Feng, Emily…Jun 11, 2024Jun 11, 2024
𝐕𝐢𝐬𝐮𝐚𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐓𝐡𝐨𝐮𝐠𝐡𝐭 𝐄𝐥𝐢𝐜𝐢𝐭𝐬 𝐒𝐩𝐚𝐭𝐢𝐚𝐥 𝐑𝐞𝐚𝐬𝐨𝐧𝐢𝐧𝐠…Imagine a scenario where you’re listening to a story. As you follow along, your mind naturally starts to visualize the the unseen objects…May 24, 2024May 24, 2024
LLMOps IntroductionI recently completed a short course called LLMOps by DeepLearning.AI, in collaboration with Google Cloud, instructed by Erwin HuizengaMay 12, 2024May 12, 2024
How to Optimize LLMs for Efficient ServingWe all know that serving LLMs in production is complicated. It requires extensive research and the design of the best architecture and…May 8, 2024May 8, 2024
Data Collection, Labeling, and Streamlined Data PipelinesHLP (Human Level Preference)May 7, 20241May 7, 20241
Mastering LLM: A Comprehensive Guide to Legal Language Model ServingWe all know that serving LLMs in production is complicated. It requires extensive research and the design of the best architecture and…May 2, 2024May 2, 2024
Mastering Data Preparation: A Comprehensive GuideWe all know that data is the most crucial element in training an AI model. Recently, we noticed the importance of this when smaller…Apr 25, 2024Apr 25, 2024
Discussing RLAIF: A SummaryReinforcement Learning from Human Feedback (RLHF) is a significant topic in AI. However, it requires substantial human intervention and…Apr 3, 2024Apr 3, 2024
Optimizing MLOps: Harnessing the Power of Data-Centric StrategiesSkewed datasetsApr 3, 2024Apr 3, 2024
Analysing Errors: A Comprehensive AnalysisFor any AI project you’re working on, it’s crucial to identify the most relevant metrics for your use case. This will allow for a more…Mar 28, 2024Mar 28, 2024
Unlocking the Power of Open Source Models: A Deep Dive with deeplearning.ai and Hugging FaceI was checking this short course by DeepLearning.AI and Hugging Face called Open Source Models with Hugging Face. It’s a really useful…Mar 20, 2024Mar 20, 2024
Mastering Advanced RAG Applications: A Short Course SummaryRecently, I completed a short course titled “Building and Evaluating Advanced RAG Applications” offered by DeepLearning.AI, LlamaIndex, and…Mar 14, 2024Mar 14, 2024
Mastering the Art of Fine-Tuning: A Comprehensive Overview of the Short Course by deeplearning.aiI completed the short course 𝐅𝐢𝐧𝐞-𝐭𝐮𝐧𝐢𝐧𝐠 𝐋𝐚𝐫𝐠𝐞 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥𝐬 by DeepLearning.AI and Lamini. Several…Feb 27, 2024Feb 27, 2024