metadata

language:
  - en
license: apache-2.0
datasets:
  - nov3630/Data4RLCoder

Model Description

RLRetriever is a retriever for repository-level code completion which disregard seemingly useful yet ultimately unhelpful reference code snippets, focusing on those more likely to contribute to accurate code generation.

Developed by: Sun Yat-sen University & Huawei Cloud Computing Technologies Co., Ltd.
Shared by [Optional]: Hugging Face
Model type: Feature Engineering
Language(s) (NLP): en
License: Apache-2.0
Related Models:
- Parent Model: RoBERTa
Resources for more information:
- Associated Paper

Citation

BibTeX:

@misc{wang2024rlcoderreinforcementlearningrepositorylevel,
      title={RLCoder: Reinforcement Learning for Repository-Level Code Completion}, 
      author={Yanlin Wang and Yanli Wang and Daya Guo and Jiachi Chen and Ruikai Zhang and Yuchi Ma and Zibin Zheng},
      year={2024},
      eprint={2407.19487},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2407.19487}, 
}

Get Started

Use the code below to get started with the model.

Click to expand

from transformers import AutoTokenizer, AutoModel
 
tokenizer = AutoTokenizer.from_pretrained("nov3630/RLRetriever")
 
model = AutoModel.from_pretrained("nov3630/RLRetriever")