Model optimization

Evolution Fine-Tuning: Using LLMs to Learn and Transfer Knowledge Across 371 Optimization Tasks

This paper introduces "Evolution Fine-Tuning" (EFT), a novel approach that uses Large Language Models (LLMs) integrated with evolutionary se

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

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

Fine-Tuned Small LLMs Outperform Larger Models at 5-30x Lower Cost with Data Curation

The article discusses how fine-tuned small language models (LLMs) can outperform larger ones at significantly lower costs (5-30x) through pr

Optimizing Deep Learning Performance Through First-Principles Reasoning

The article discusses improving deep learning model performance by reasoning from first principles rather than relying on ad-hoc tricks and

Building an Abstract Interpreter for Toy IR Optimization

This blog post introduces an abstract interpreter for the Toy IR (intermediate representation) and demonstrates how to use it for simple opt