tags:
- bert
Model Card for ernie-gram
Model Details
Model Description
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding.
- Developed by: Dongling Xiao, Yukun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu and Haifeng Wang
- Shared by [Optional]: Peterchou
- Model type: More information needed
- Language(s) (NLP): Chinese, English (more information needed)
- License: More information needed
- Related Models:
- Parent Model: BERT
- Resources for more information:
Uses
Direct Use
More information needed
Downstream Use [Optional]
This model could also be used for the task of question answering and text classification.
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) 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
The model creators note in the associated paper:
English Pre-training Data. We use two com- mon text corpora for English pre-training: • Base-scale corpora: 16GB uncompressed text from WIKIPEDIA and BOOKSCORPUS (Zhu et al., 2015), which is the original data for BERT. • Large-scale corpora: 160GB uncompressed text from WIKIPEDIA, BOOKSCORPUS, OPEN- WEBTEXT3, CC-NEWS (Liu et al., 2019) and STORIES (Trinh and Le, 2018), which is the original data used in RoBERTa.
Chinese Pre-training Data. We adopt the same Chinese text corpora used in ERNIE2.0 (Sun et al., 2020) to pre-train ERNIE-Gram.
Training Procedure
Preprocessing
The model authors note in the associated paper:
For pre-training on base-scale English corpora, the batch size is set to 256 sequences, the peak learning rate is 1e-4 for 1M training steps, which are the same settings as BERTBASE. As for large-scale English corpora, the batch size is 5112 sequences, the peak learning rate is 4e-4 for 500K training steps. For pre-training on Chinese corpora, the batch size is 256 sequences, the peak learning rate is 1e-4 for 3M training steps.
Speeds, Sizes, Times
More information needed
Evaluation
Testing Data, Factors & Metrics
Testing Data
More information needed
Factors
Metrics
More information needed
Results
Classification and matching use the CLUE dataset. CLUE evaluation results:
| 配置 | 模型 | CLUEWSC2020 | IFLYTEK | TNEWS | AFQMC | CMNLI | CSL | OCNLI | 平均值 |
|---|---|---|---|---|---|---|---|---|---|
| 20L1024H | ERNIE 3.0-XBase | 91.12 | 62.22 | 60.34 | 76.95 | 84.98 | 84.27 | 82.07 | 77.42 |
| 12L768H | ERNIE 3.0-Base | 88.18 | 60.72 | 58.73 | 76.53 | 83.65 | 83.30 | 80.31 | 75.63 |
| 6L768H | ERNIE 3.0-Medium | 79.93 | 60.14 | 57.16 | 74.56 | 80.87 | 81.23 | 77.02 | 72.99 |
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:
@article{xiao2020ernie,
title={ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding},
author={Xiao, Dongling and Li, Yu-Kun and Zhang, Han and Sun, Yu and Tian, Hao and Wu, Hua and Wang, Haifeng},
journal={arXiv preprint arXiv:2010.12148},
year={2020}
}
Glossary [optional]
More information needed
More Information [optional]
More information needed
Model Card Authors [optional]
Peterchou 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.
Click to expand
from transformers import AutoModel
model = AutoModel.from_pretrained("peterchou/ernie-gram")