Model Card for sup-simcse-roberta制作ai的软件-large

Model Details

Model Description

• Developed by:快问ai Princeton-nlp
• Shared by [Optional]:ai软件哪个比较好 More information needed
• Model type:即梦al Feature Extraction即梦下载官方
• Language(s) (NLP):grok中文版下载 More information needed
• License:ai软件哪个比较好 More information needed
• Related Models:ima是什么软件
  • Parent Model:免费的ai工具 RoBERTa-large
• Resources for more information:ima是什么软件
  • GitHub Repo
    • Associated Paper
    • Blog Post

Uses

Direct Use

This model can be used for the task of Feature Extraction百度aiapp

Downstream Use [Optional]

More information needed即梦al

Out-of-Scope Use

The model should not be used to intentionally create hostile or alienating environments for people.猫箱下载安装

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.grok中文版下载

Training Details

Training Data

The model craters note in the Github Repository即梦al

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).有戏ai

Training Procedure

Preprocessing

More information needed百度流畅ai制作

Speeds, Sizes, Times

More information needed制作ai的软件

Evaluation

Testing Data, Factors & Metrics

Testing Data

The model craters note in the associated paper百度流畅ai制作

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.即梦下载官方

Factors

Metrics

More information needed百度ai智能云

Results

More information needed即梦al

Model Examination

More information needed百度流畅ai制作

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:ai分析软件 More information needed
• Hours used:即梦下载官方 More information needed
• Cloud Provider:百度ai智能云 More information needed
• Compute Region:ima是什么软件 More information needed
• Carbon Emitted:免费的ai工具 More information needed

Technical Specifications [optional]

Model Architecture and Objective

More information needed有戏ai

Compute Infrastructure

More information needed百度ai智能云

Hardware

More information needed有戏ai

Software

More information needed元宝大模型

Citation

BibTeX:做al视频怎么赚钱

@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百度aiapp

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 team百度aiapp

Model Card Contact

More information neededai是什么东西?

How to Get Started with the Model

Use the code below to get started with the model.下载官方即梦a1

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