Model optimization guide

A Framework for Systematic Prompt Optimization as Model Selection

This article presents a framework for prompt optimization in AI/ML systems, treating it as a model selection problem. It emphasizes defining

Understanding Reinforcement Learning for Model Training, and future directions with GRAPE

Understanding Quantization: A Guide to Model Compression Techniques

A comprehensive guide to quantization, explaining what it is, how it works, and its application in compressing large language models. The ar

Systematic Evaluation of Deep Learning Optimizers Reveals Limited Speedup Over AdamW in Language Model Pretraining

This research paper systematically evaluates ten deep learning optimizers for language model pretraining, challenging previous claims of 1.4

Optimizing Datalog for the GPU

LLMs vs. Classical HPO Algorithms: Hybrid Approach Outperforms Both in Hyperparameter Optimization

This research paper compares classical hyperparameter optimization (HPO) algorithms (CMA-ES, TPE) against LLM-based methods for tuning a sma

LLMs vs. Classical HPO Algorithms: Hybrid Approach Outperforms Both in Hyperparameter Optimization

This research paper compares classical hyperparameter optimization (HPO) algorithms (CMA-ES, TPE) against LLM-based methods for tuning a sma