Vivek PanditLost in the Middle: How Language Models Use Long ContextsIn recent years, the capabilities of language models have expanded significantly, with advancements allowing these models to process and…Aug 17Aug 17
Vivek PanditRouteLLM: Optimizing the Cost-Quality Trade-Off in Large Language Model DeploymentIntroductionJul 26Jul 26
Vivek PanditDo you really need prompt engineering?DSPy is a framework designed to optimize language model (LM) prompts and weights, particularly for complex systems using LMs in a pipeline…Jun 15Jun 15
Vivek PanditDirect Preference Optimization(DPO): Advancing Beyond Traditional Reinforcement LearningThere is lot of research going on in AI, specially on LLMs. This research could be making us rethinking about how we have been doing AI in…Apr 171Apr 171
Vivek PanditPrompt EngineeringWhile there is still a lot of research going on in the area of how to improve LLMs in the areas of Model Efficiency, Generalisation, Bias…May 5, 2023May 5, 2023
Vivek PanditMeta’s LLaMA, new kid on the blockFor the past few weeks, the language models created and used by Microsoft, Google, and OpenAI have received a lot of attention in the IT…Mar 3, 2023Mar 3, 2023