Downloads · 30 days
58.6K
2% of all-time downloads
bert-toxic-comment-classification
JungleLee/bert-toxic-comment-classification
bert-toxic-comment-classification is a text classification model from JungleLee. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as afl-3.0.
This model is a fine-tuned version of the bert-base-uncased model to classify toxic comments.
All-time downloads
2.5M
Public
Repo size
1.3 GB
Likes
23
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- afl-3.0
- Model type
- bert
- Access
- Public
- Created
- Mar 10, 2023
- Updated
- Mar 28, 2023
- SHA
- 9c591042
Try a prompt
Model card
From the Hugging Face model README
Model description
This model is a fine-tuned version of the bert-base-uncased model to classify toxic comments.
How to use
You can use the model with the following code.
from transformers import BertForSequenceClassification, BertTokenizer, TextClassificationPipeline
model_path = "JungleLee/bert-toxic-comment-classification"
tokenizer = BertTokenizer.from_pretrained(model_path)
model = BertForSequenceClassification.from_pretrained(model_path, num_labels=2)
pipeline = TextClassificationPipeline(model=model, tokenizer=tokenizer)
print(pipeline("You're a fucking nerd."))
Training data
The training data comes from this Kaggle competition. We use 90% of the train.csv data to train the model.
Evaluation results
The model achieves 0.95 AUC in a 1500 rows held-out test set.
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- afl-3.0
- Languages
- en
- Hf Inference
- live
- Created
- Mar 10, 2023
- Updated
- Mar 28, 2023