Halfotter/korean-xlm-roberta-classifier

Korean XLM-RoBERTa Classifier (HF Compatible)

This model is converted from a custom classifier to be compatible with Hugging Face Inference API.

Model Info

• Base Model: xlm-roberta-base
• Task: text-classification
• Language: Korean
• Labels: 66

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load directly from Hugging Face Hub
tokenizer = AutoTokenizer.from_pretrained("Halftotter/korean-xlm-roberta-classifier")
model = AutoModelForSequenceClassification.from_pretrained("Halftotter/korean-xlm-roberta-classifier")

# Predict
inputs = tokenizer("원본 투입물명", return_tensors="pt")
outputs = model(**inputs)
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
print(predictions)