Downloads · 30 days
16
2% of all-time downloads
intent-classification-korean
gg4ever/intent-classification-korean
intent-classification-korean is a text classification model from gg4ever. 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.
fine-tuned for 'klue/roberta-base' used data : 'kor3i4k'
All-time downloads
800
Public
Repo size
885 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin443 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- roberta
- Access
- Public
- Created
- Aug 30, 2023
- Updated
- Aug 30, 2023
- SHA
- ce58aca8
Datasets
Model card
From the Hugging Face model README
intent-classification-korean
fine-tuned for 'klue/roberta-base' used data : 'kor_3i4k'
How to Get Started with the Model
from transformers import TextClassificationPipeline
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model_path = "gg4ever/intent-classifcation-korean"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)
text_classifier = TextClassificationPipeline(
tokenizer=tokenizer,
model=model.to('cpu'),
return_all_scores=True
)
# predict
text = "이름이 뭐에요?"
preds_list = text_classifier(text)
preds_list
Training Hyperparameters
| hyperparameters | values |
|---|---|
| predict_with_generate | True |
| evaluation_strategy | "steps" |
| per_device_train_batch_size | 32 |
| per_device_eval_batch_size | 32 |
| num_train_epochs | 3 |
| learning_rate | 4e-5 |
| warmup_steps | 1000 |
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- apache-2.0
- Languages
- ko
- Created
- Aug 30, 2023
- Updated
- Aug 30, 2023