Model Card for UniXcoder-base

Model Details

Model Description

UniXcoder is a unified cross-modal pre-trained model that leverages multimodal data (i.e. code comment and AST) to pretrain code representation.元宝大模型

• Developed by:下载官方即梦a1 Microsoft Team
• Shared by [Optional]:制作ai的软件 Hugging Face
• Model type:有戏ai Feature Engineering
• Language(s) (NLP):有戏ai en
• License:ai是什么东西? Apache-2.0
• Related Models:百度aiapp
  • Parent Model:grok中文版下载 roberta百度ai智能云
• Resources for more information:人工智能ai哪个好
  • Associated Paper

Uses

Direct Use

Feature Engineeringgrok中文版下载

Downstream Use [Optional]

More information needed元宝大模型

Out-of-Scope Use

More information neededai软件哪个比较好

Bias, Risks, and Limitations

Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.免费的ai工具

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.做al视频怎么赚钱

Training Details

Training Data

More information needed百度流畅ai制作

Training Procedure

Preprocessing

More information neededai软件哪个比较好

Speeds, Sizes, Times

More information needed百度ai智能云

Evaluation

Testing Data, Factors & Metrics

Testing Data

More information needed猫箱下载安装

Factors

The model creators note in the associated paper:百度aiapp

UniXcoder has slightly worse BLEU-4 scores on both code summarization and generation tasks. The main reasons may come from two aspects. One is the amount of NL-PL pairs in the pre-training data快问ai

Metrics

The model creators note in the associated paper:元宝大模型

We evaluate UniXcoder on five tasks over nine public datasets, including two understanding tasks, two generation tasks and an autoregressive task. To further evaluate the performance of code fragment embeddings, we also propose a new task called zero-shot code-to-code search.快问ai

Results

The model creators note in the associated paper:快问ai

Taking zero-shot code-code search task as an example, after removing contrastive learning, the performance drops from 20.45% to 13.73%.做al视频怎么赚钱

Model Examination

More information neededai分析软件

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).有戏ai

• Hardware Type:即梦下载官方 More information needed
• Hours used:grok中文版下载 More information needed
• Cloud Provider:百度流畅ai制作 More information needed
• Compute Region:做al视频怎么赚钱 More information needed
• Carbon Emitted:人工智能ai哪个好 More information needed

Technical Specifications [optional]

Model Architecture and Objective

More information needed即梦al

Compute Infrastructure

More information needed下载官方即梦a1

Hardware

More information needed做al视频怎么赚钱

Software

More information neededal一键脱装入口

Citation

BibTeX:百度流畅ai制作

@misc{https://doi.org/10.48550/arxiv.2203.03850,
 doi = {10.48550/ARXIV.2203.03850},
 url = {https://arxiv.org/abs/2203.03850},
 author = {Guo, Daya and Lu, Shuai and Duan, Nan and Wang, Yanlin and Zhou, Ming and Yin, Jian},
 keywords = {Computation and Language (cs.CL), Programming Languages (cs.PL), Software Engineering (cs.SE), FOS: Computer and information sciences, FOS: Computer and information sciences},
 title = {UniXcoder: Unified Cross-Modal Pre-training for Code 

Glossary [optional]

More information needed免费的ai工具

More Information [optional]

More information needed即梦al

Model Card Authors [optional]

Microsoft Team in collaboration with Ezi Ozoani and the Hugging Face Team.al一键脱装入口

Model Card Contact

More information neededima是什么软件

How to Get Started with the Model

Use the code below to get started with the model.百度aiapp

from Transformers制作ai的软件 import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("microsoft/unixcoder-base")
model = AutoModel.from_pretrained("microsoft/unixcoder-base")