This repository contains the source code of our paper. Part of the code is borrowed from in-context-learning.
Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning
Yingcong Li, Kartik Sreenivasan, Angeliki Giannou, Dimitris Papailiopoulos, Samet Oymak
Paper: https://arxiv.org/pdf/2301.07067.pdf
Follow in-context-learning's instruction by runing
conda env create -f environment.yml
conda activate in-context-learning
- Enter into directory
src
- Run
train.py
based on the choosen config file:python train.py --config conf/[config_file].yaml
- Enter into directory
src
- Refer to the
eval.ipynb
file
If you have any question, please contact Yingcong Li ([email protected])