|
--- |
|
|
|
|
|
{} |
|
--- |
|
|
|
# Model Card for distilbert-base-task-multi-label-classification Model |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
This model is based on the distillation of the BERT base model, which is a widely used language model. |
|
The distillation process involves training a smaller model to mimic the behavior and predictions of the larger BERT model. |
|
The purpose of this model is to perform fine-tuning on the distilbert-base-pwc-task-multi-label-classification checkpoint for multi-label classification tasks. |
|
|
|
Fine-tuning approach can be applied to other models such as RoBERTa, DeBERTa, DistilBERT, CANINE, and more. The notebook provides a practical guide for utilizing these models in various classification scenarios. |
|
|
|
|
|
- **Developed by:** Lina Saba |
|
- **Model type:** bert for multi-label classification |
|
- **Language(s) (NLP):** Python |
|
- **Finetuned from model:** distilbert-base-pwc-task-multi-label-classification |
|
|
|
### Model Sources [optional] |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** https://colab.research.google.com/drive/1Z314gK2qixK_0ujgQ3nvqvar1iV3QnoF?usp=sharing |
|
- **Paper [optional]:** [More Information Needed] |
|
- **Demo [optional]:** [More Information Needed] |
|
|
|
## Uses |
|
|
|
This model aims to fine-tune BERT to predict one or more labels for a given piece of text. |
|
The related notebook illustrates how to fine-tune a distilbert-base-pwc-task-multi-label-classification model, Knowing that it's the same way to fine-tune a RoBERTa, DeBERTa, DistilBERT, CANINE, ... checkpoint. |
|
|
|
### Direct Use |
|
|
|
Predict the labels of a piece of text from this |
|
list = { |
|
0: 'aspersion', |
|
1: 'hyperbole', |
|
2: 'lying', |
|
3: 'namecalling', |
|
4: 'noncooperation', |
|
5: 'offtopic', |
|
6: 'other_incivility', |
|
7: 'pejorative', |
|
8: 'sarcasm', |
|
9: 'vulgarity' |
|
} |
|
|
|
### Downstream Use [optional] |
|
|
|
This model is fine-tuned on a dataset; a collection of more than 6000 comments on Arizona Daily Star news articles |
|
from 2011 that have been manually annotated for various forms of incivility including aspersion, namecalling, sarcasm, and vulgarity. |
|
|
|
## Bias, Risks, and Limitations |
|
|
|
Technical limitations : |
|
- Can't print more than one identified label using pipeline. |
|
- Half of the test results aren't exactly the same as what expected |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> |
|
|
|
[More Information Needed] |
|
|
|
### Training Procedure |
|
|
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> |
|
|
|
#### Preprocessing [optional] |
|
|
|
[More Information Needed] |
|
|
|
|
|
#### Training Hyperparameters |
|
|
|
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> |
|
|
|
#### Speeds, Sizes, Times [optional] |
|
|
|
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> |
|
|
|
[More Information Needed] |
|
|
|
## Evaluation |
|
|
|
<!-- This section describes the evaluation protocols and provides the results. --> |
|
|
|
### Testing Data, Factors & Metrics |
|
|
|
#### Testing Data |
|
|
|
<!-- This should link to a Data Card if possible. --> |
|
|
|
[More Information Needed] |
|
|
|
#### Factors |
|
|
|
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> |
|
|
|
[More Information Needed] |
|
|
|
#### Metrics |
|
|
|
<!-- These are the evaluation metrics being used, ideally with a description of why. --> |
|
|
|
[More Information Needed] |
|
|
|
### Results |
|
|
|
[More Information Needed] |
|
|
|
#### Summary |
|
|
|
|
|
|
|
## Model Examination [optional] |
|
|
|
<!-- Relevant interpretability work for the model goes here --> |
|
|
|
[More Information Needed] |
|
|
|
## Environmental Impact |
|
|
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> |
|
|
|
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:** [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 [optional] |
|
|
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> |
|
|
|
**BibTeX:** |
|
|
|
[More Information Needed] |
|
|
|
**APA:** |
|
|
|
[More Information Needed] |
|
|
|
## Glossary [optional] |
|
|
|
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> |
|
|
|
[More Information Needed] |
|
|
|
## More Information [optional] |
|
|
|
[More Information Needed] |
|
|
|
## Model Card Authors [optional] |
|
|
|
[More Information Needed] |
|
|
|
## Model Card Contact |
|
|
|
[More Information Needed] |
|
|
|
|
|
|
