From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
Implementation for paper "From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data"
To install the environment, run
conda env create -f environment.yml
conda activate needle
To generate the data
cd data-generation
cd scripts
bash run.sh