Shuyang XianginTowards Data ScienceUnder-trained and Unused tokens in Large Language ModelsExistence of under-trained and unused tokens and Identification Techniques using GPT-2 Small as an Example17h ago17h ago
Shuyang XianginTowards Data ScienceKernelSHAP can be misleading with correlated predictorsA concrete case studyAug 9Aug 9
Shuyang XiangBuilding a Smarter Math Solver than Basic LLMIntegrating a Condition Mining Maths Agent to Assist LLM with Complex ProblemsJul 191Jul 191
Shuyang XianginTowards Data ScienceCreating an Assistant with OpenAI Assistant API and StreamlitA step-by-step guideJun 181Jun 181
Shuyang XianginTowards Data ScienceCan Neural Networks Formulate Shock Wave?How we build a PINN for inviscid Burgers Equation with shock formulationApr 4Apr 4
Shuyang XianginTowards Data ScienceHow to Interpret GPT2-SmallMechanistic Interpretability on prediction of repeated tokensMar 22Mar 22
Shuyang XianginTowards AIHow Can AI Help Visually Impaired People See The WorldAn attempt to craft an App empowered by LLM to support the visually impairedDec 28, 2023Dec 28, 2023
Shuyang XiangHow to unleash the Power of SQL Responses with Multifaceted in ChatbotsUsing Langchains and ChatGPTDec 15, 2023Dec 15, 2023
Shuyang XianginTowards Data ScienceChallenges in Stop Generation within Llama 2An Exploration with Potential SolutionsSep 10, 20234Sep 10, 20234
Shuyang XianginTowards Data ScienceEnhancing CSV File Query Performance in ChatGPTwith LangChain’s Self-Querying based on a customized CSV LoaderJul 31, 20233Jul 31, 20233