[!NOTE] This is an unofficial reupload of microsoft/unixcoder-base in the
SafeTensorsformat usingtransformers4.40.1. The goal of this reupload is to prevent older models that are still relevant baselines from becoming stale as a result of changes in HuggingFace. Additionally, I may include minor corrections, such as model max length configuration.
Original model card below:
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.
- Developed by: Microsoft Team
- 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:
Uses
Direct Use
Feature Engineering
Downstream Use [Optional]
More information needed
Out-of-Scope Use
More information needed
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.
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.
Training Details
Training Data
More information needed
Training Procedure
Preprocessing
More information needed
Speeds, Sizes, Times
More information needed
Evaluation
Testing Data, Factors & Metrics
Testing Data
More information needed
Factors
The model creators note in the associated paper:
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
Metrics
The model creators note in the associated paper:
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.
Results
The model creators note in the associated paper:
Taking zero-shot code-code search task as an example, after removing contrastive learning, the performance drops from 20.45% to 13.73%.
Model Examination
More information needed
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: More information needed
- Hours used: More information needed
- Cloud Provider: More information needed
- Compute Region: More information needed
- Carbon Emitted: More information needed
Technical Specifications [optional]
Model Architecture and Objective
More information needed
Compute Infrastructure
More information needed
Hardware
More information needed
Software
More information needed
Citation
BibTeX:
@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
More Information [optional]
More information needed
Model Card Authors [optional]
Microsoft Team in collaboration with Ezi Ozoani and the Hugging Face Team.
Model Card Contact
More information needed
How to Get Started with the Model
Use the code below to get started with the model.
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("microsoft/unixcoder-base")
model = AutoModel.from_pretrained("microsoft/unixcoder-base")