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