Published inTowards Data ScienceTransformers: From NLP to Computer VisionHow Transformer architecture has been adapted to computer vision tasksMay 5, 20241May 5, 20241
Published inTowards Data ScienceOptimizing Multi-task Learning Models in PracticeWhat is multi-task learning models, and how to optimize themMar 29, 2024Mar 29, 2024
Published inTowards Data ScienceCorrect Sampling Bias for Recommender SystemsWhat is sampling bias in recommendation, and how to correct themOct 1, 20231Oct 1, 20231
Published inTowards Data ScienceA Quick Guide on Normalization for Your NLP ModelAccelerate your model convergence and stabilize the training process with normalizationSep 14, 20231Sep 14, 20231
Published inTowards AIBuild Your First Autocorrection without Machine LearningA step-by-step guide to building your own spell checker.Sep 3, 20231Sep 3, 20231
Guiding LLM with Reinforcement Learning from Human Feedback — Part 1Ever wonder why ChatGPT won’t tell you how to make a bomb?Aug 28, 2023Aug 28, 2023
Published inTowards Data ScienceBERT vs GPT: Comparing the NLP GiantsHow different are their structure, and how do the differences impact the model’s ability?Aug 20, 20231Aug 20, 20231
Published inTowards Data ScienceLeveraging LLMs with Information Retrieval: A Simple DemoA demo of integrating a Question-Answering LLM with retrieval componentsAug 14, 20231Aug 14, 20231
A Quick Guide to Fine-tuning Techniques for Large Language ModelsLarge language models (LLM) have transformed the field of natural language processing (NLP) with their remarkable text understanding and…Jul 15, 20232Jul 15, 20232
