Model Card for unsup-simcse-bert百度流畅ai制作-base-uncased

Model Details

Model Description

More information neededai是什么东西?

• Developed by:百度流畅ai制作 Princeton NLP group
• Shared by [Optional]:做al视频怎么赚钱 Hugging Face
• Model type:猫箱下载安装 Feature Extraction制作ai的软件
• Language(s) (NLP):人工智能ai哪个好 More information needed
• License:grok中文版下载 More information needed
• Related Models:即梦下载官方
  • Parent Model:百度流畅ai制作 BERT
• Resources for more information:快问ai
  • GitHub Repo
  • Model Space
  • Associated Paper

Uses

Direct Use

This model can be used for the task of Feature Engineering.百度ai智能云

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.即梦al

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.百度流畅ai制作

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.制作ai的软件

Training Details

Training Data

The model craters note in the Github Repository免费的ai工具

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).即梦下载官方

Training Procedure

Preprocessing

More information needed做al视频怎么赚钱

Speeds, Sizes, Times

More information neededai软件哪个比较好

Evaluation

Testing Data, Factors & Metrics

Testing Data

The model craters note in the associated paper即梦al

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.grok中文版下载

Factors

More information neededai分析软件

Metrics

More information neededai是什么东西?

Results

More information needed即梦al

Model Examination

The model craters note in the associated paper有戏ai

Uniformity and alignment.人工智能ai哪个好
We also observe that (1) though pre-trained embeddings have good alignment, their uniformity is poor (i.e., the embeddings are highly anisotropic); (2) post-processing methods like BERT-flow and BERT-whitening greatly improve uniformity but also suffer a degeneration in alignment; (3) unsupervised SimCSE effectively improves uniformity of pre-trained embeddings whereas keeping a good alignment;(4) incorporating supervised data in SimCSE further amends alignment.

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).人工智能ai哪个好

• Hardware Type:即梦al Nvidia 3090 GPUs with CUDA 11
• Hours used:grok中文版下载 More information needed
• Cloud Provider:猫箱下载安装 More information needed
• Compute Region:ai软件哪个比较好 More information needed
• Carbon Emitted:有戏ai More information needed

Technical Specifications [optional]

Model Architecture and Objective

More information needed免费的ai工具

Compute Infrastructure

More information neededai分析软件

Hardware

More information neededai分析软件

Software

More information needed制作ai的软件

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免费的ai工具

More Information [optional]

More information neededai分析软件

Model Card Authors [optional]

Princeton NLP group in collaboration with Ezi Ozoani and the Hugging Face teamai分析软件

Model Card Contact

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!

How to Get Started with the Model

Use the code below to get started with the model.ai分析软件

from Transformers百度ai智能云 import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/unsup-simcse-bert-base-uncased")
model = AutoModel.from_pretrained("princeton-nlp/unsup-simcse-bert-base-uncased")