---
license: cc-by-nc-4.0
---

## Model Description

**StarEncoder** trained with training split of `retrieval_nl_code` subset of [xCodeEval](https://huggingface.co/datasets/NTU-NLP-sg/xCodeEval). Trained for 37 epochs. 

Code Repo used to train: https://github.com/facebookresearch/DPR        

For details result, please follow our [paper](https://arxiv.org/abs/2303.03004).