Instructions to use microsoft/unixcoder-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/unixcoder-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="microsoft/unixcoder-base")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("microsoft/unixcoder-base") model = AutoModel.from_pretrained("microsoft/unixcoder-base", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
| language: code | |
| license: apache-2.0 | |
| # UniXcoder | |
| ## Model description | |
| UniXcoder is a unified cross-modal pre-trained model for programming languages to support both code-related understanding and generation tasks. The model can support six languages: java, ruby, python, php, javascript, and go. | |
| [UniXcoder: Unified Cross-Modal Pre-training for Code Representation.](https://arxiv.org/abs/2203.03850) Daya Guo, Shuai Lu, Nan Duan, Yanlin Wang, Ming Zhou, Jian Yin. | |
| [GitHub](hhttps://github.com/microsoft/CodeBERT/tree/master/UniXcoder#unixcoder) | |
| ## Citation | |
| If you use UniXcoder, please consider citing the following paper: | |
| ``` | |
| @article{guo2022unixcoder, | |
| title={UniXcoder: Unified Cross-Modal Pre-training for Code Representation}, | |
| author={Guo, Daya and Lu, Shuai and Duan, Nan and Wang, Yanlin and Zhou, Ming and Yin, Jian}, | |
| journal={arXiv preprint arXiv:2203.03850}, | |
| year={2022} | |
| } | |
| ``` | |