You may need a single 80G GPU to run the experiment. We experiment on CUDA 11.8 and torch 2.0.1. Setup up a new conda env and install necessary packages. conda create ...
This repository contains code for Talk like a Graph: Encoding Graphs for Large Language Models and Let Your Graph Do the Talking: Encoding Structured Data for LLMs. @inproceedigs{fatemi2024talk, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results