Model Card for Roberta-toxic
RoBERTa-toxic: A Robust Toxicity Prediction Model
RoBERTa-toxic leverages the power of the RoBERTa (Robustly Optimized BERT Pretraining Approach) transformer model to analyze text inputs and predict an array of toxicity categories. Fine-tuned for identifying nuanced toxic behaviors such as hate speech, harassment, profanity, and harmful stereotypes, it delivers accurate, context-aware predictions. The model is tailored for applications like content moderation, social media analysis, and safe online interactions, providing multi-label outputs for comprehensive toxicity profiling.
Model Details
Model Description
- Developed by: ESIEA Students
- Shared by [optional]: ESIEA Students
- Model type: Roberta with additionnal layer to predict array of booleans
- Language(s) (NLP): English
- Finetuned from model [optional]: Roberta
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
The model can be used to classify text based on their toxicities
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
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.
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
We did train the model on the googleJigSaw toxic dataset as mentionned above on the 150k comments
[More Information Needed]
Training Procedure
we trained
Preprocessing [optional]
we only did some basic data-cleaning
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
training time 4hours on a gtx 1050TI GPU on 3 epochs
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
Accuracy of : 90%
[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: GTX 1050 TI
- Hours used: 4 HOURS
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
We did use torch
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]
