Model Card for sup-simcse-roberta下载官方即梦a1-large

Model Details

Model Description

• Developed by:百度aiapp Princeton-nlp
• Shared by [Optional]:ai是什么东西? More information needed
• Model type:下载官方即梦a1 Feature Extractionai软件哪个比较好
• Language(s) (NLP):al一键脱装入口 More information needed
• License:百度aiapp More information needed
• Related Models:下载官方即梦a1
  • Parent Model:ai软件哪个比较好 RoBERTa-large
• Resources for more information:下载官方即梦a1
  • GitHub Repo
    • Associated Paper
    • Blog Post

Uses

Direct Use

This model can be used for the task of Feature Extraction制作ai的软件

Downstream Use [Optional]

More information neededal一键脱装入口

Out-of-Scope Use

The model should not be used to intentionally create hostile or alienating environments for people.ai分析软件

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.做al视频怎么赚钱

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.al一键脱装入口

Training Details

Training Data

The model craters note in the Github Repositoryal一键脱装入口

We train unsupervised SimCSE on 106 randomly sampled sentences from English Wikipedia, and train supervised SimCSE on the combination of MNLI and SNLI datasets (314k).ai分析软件

Training Procedure

Preprocessing

More information needed免费的ai工具

Speeds, Sizes, Times

More information needed快问ai

Evaluation

Testing Data, Factors & Metrics

Testing Data

The model craters note in the associated paperai软件哪个比较好

Our evaluation code for sentence embeddings is based on a modified version of SentEval. It evaluates sentence embeddings on semantic textual similarity (STS) tasks and downstream transfer tasks. For STS tasks, our evaluation takes the “all” setting, and report Spearman’s correlation. See associated paper (Appendix B) for evaluation details.人工智能ai哪个好

Factors

Metrics

More information needed百度aiapp

Results

More information neededai是什么东西?

Model Examination

More information needed快问ai

Environmental Impact

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

• Hardware Type:百度ai智能云 More information needed
• Hours used:制作ai的软件 More information needed
• Cloud Provider:ai分析软件 More information needed
• Compute Region:百度流畅ai制作 More information needed
• Carbon Emitted:ai分析软件 More information needed

Technical Specifications [optional]

Model Architecture and Objective

More information neededal一键脱装入口

Compute Infrastructure

More information needed百度ai智能云

Hardware

More information needed做al视频怎么赚钱

Software

More information needed制作ai的软件

Citation

BibTeX:grok中文版下载

@inproceedings{gao2021simcse,
  title={{SimCSE}: Simple Contrastive Learning of Sentence Embeddings},
  author={Gao, Tianyu and Yao, Xingcheng and Chen, Danqi},
  booktitle={Empirical Methods in Natural Language Processing (EMNLP)},
  year={2021}
}

Glossary [optional]

More information needed有戏ai

More Information [optional]

If you have any questions related to the code or the paper, feel free to email Tianyu (tianyug@cs.princeton.edu) and Xingcheng (yxc18@mails.tsinghua.edu.cn). If you encounter any problems when using the code, or want to report a bug, you can open an issue. Please try to specify the problem with details so we can help you better and quicker!

Model Card Authors [optional]

Princeton NLP group in collaboration with Ezi Ozoani and the Hugging Face teamima是什么软件

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.ai是什么东西?

from Transformers快问ai import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/sup-simcse-roberta-large")
model = AutoModel.from_pretrained("princeton-nlp/sup-simcse-roberta-large")