Downloads · 30 days
16
1% of all-time downloads
bert-base-uncased-ade-Ade-corpus-v2
Jorgeutd/bert-base-uncased-ade-Ade-corpus-v2
bert-base-uncased-ade-Ade-corpus-v2 is a text classification model from Jorgeutd. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
All-time downloads
1.5K
Public
Parameters
109M
876 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 50%
Parameter types
How the weights are stored.
F32109M · 100%
Try a prompt
Datasets
Model card
From the Hugging Face model README
bert-base-uncased
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
- Problem type: Text Classification(adverse drug effects detection).
Hyperparameters
{
"do_eval": true,
"do_train": true,
"fp16": true,
"load_best_model_at_end": true,
"model_name": "bert-base-uncased",
"num_train_epochs": 10,
"per_device_eval_batch_size": 16,
"per_device_train_batch_size": 16,
"learning_rate":5e-5
}
Validation Metrics
| key | value |
|---|---|
| eval_accuracy | 0.9298021697511167 |
| eval_auc | 0.8902672664394546 |
| eval_f1 | 0.827315541601256 |
| eval_loss | 0.17835010588169098 |
| eval_recall | 0.8234375 |
| eval_precision | 0.831230283911672 |
Usage
You can use cURL to access this model:
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I got a rash from taking acetaminophen"}' https://api-inference.huggingface.co/models/Jorgeutd/bert-base-uncased-ade-Ade-corpus-v2
"""
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- Mar 2, 2022
- Updated
- Jul 13, 2023