---
tags:
- feature-extraction
- bert
---

# Model Card for unsup-simcse-bert-large-uncased 
 
# Model Details
 
## Model Description
 
More information needed
 
- **Developed by:** Princeton NLP group
- **Shared by [Optional]:** Princeton NLP group

- **Model type:** Feature Extraction
- **Language(s) (NLP):** More information needed
- **License:** More information needed
- **Parent Model:** BERT
- **Resources for more information:**
 	- [GitHub Repo](https://github.com/princeton-nlp/SimCSE)
 	 - [Associated Paper](https://arxiv.org/abs/2104.08821)


# Uses
 

## Direct Use
This model can be used for the task of feature extraction. 
 
## Downstream Use [Optional]
 
More information needed.
 
## Out-of-Scope Use
 
The model should not be used to intentionally create hostile or alienating environments for people. 
 
# Bias, Risks, and Limitations
 
 
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). 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
 
  The model craters note in the [associatedGithub Repository](https://github.com/princeton-nlp/SimCSE/blob/main/README.md):
> 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).
 
 
 
## Training Procedure

 
### Preprocessing
 
More information needed 


 
### Speeds, Sizes, Times
 
 
**Hyperparameters**
The model craters note in the [associated GitHub Repo](https://github.com/princeton-nlp/SimCSE) : 
 
|               | Unsup. BERT | Sup.      |
|:--------------|:-----------:|:---------:|
| Batch size    | 64          | 512       |
| Learning rate (large) | 1e-5 | 1e-5 |
 


 
# Evaluation
 
 
## Testing Data, Factors & Metrics
 
### Testing Data
 
 The model craters note in the [associated paper](https://arxiv.org/pdf/2104.08821.pdf):
> Our evaluation code for sentence embeddings is based on a modified version of [SentEval](https://github.com/facebookresearch/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](https://arxiv.org/pdf/2104.08821.pdf) (Appendix B) for evaluation details.


 
### Factors
More information needed
 
### Metrics
 
More information needed
 
 
## Results 
 
More information needed

 
# Model Examination
 
 The model craters note in the [associated paper](https://arxiv.org/pdf/2104.08821.pdf):
 
>**Uniformity and alignment.**
 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](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
- **Hardware Type:** Nvidia 3090 GPUs with CUDA 11
- **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:**
 
 
```bibtex
@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

# More Information [optional]
More information needed 

 
# Model Card Authors [optional]
 
Princeton NLP group in collaboration with Ezi Ozoani and the Hugging Face team.

# 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.
 
<details>
<summary> Click to expand </summary>

```python
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/unsup-simcse-bert-large-uncased")

model = AutoModel.from_pretrained("princeton-nlp/unsup-simcse-bert-large-uncased")
 ```
</details>