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]

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

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[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 [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]