IEEE

LLM on FPGA: Squeezing Language Models by Quantization and Multi-Query Attention and its Efficient Hardware Architecture

Abstract: We present an on-chip implementation of a compressed Transformer-based language model on a Xilinx Artix-7 FPGA. Our contributions include: (1) combining ultra-low-precision quantization (4 ...
IEEE

HITSQL: Human-In-The-Loop Techniques for Enhancing Text-to-SQL Query Generation with Large Language Models

Abstract: This paper presents a novel model we called HIT-SQL to enhance text-to-SQL query generation using large language models (LLMs) with progressive active learning. HITSQL is specifically ...