Downloads · 30 days
6
1% of all-time downloads
blue2959/xlm-roberta-base-finetuned-kor-8-emotions_v1.2
xlm-roberta-base-finetuned-kor-8-emotions_v1.2 is a text classification model from blue2959. Use it when you need a label for a piece of text. It is set up for transformers.
- labeldictionary - emo2int = { "기쁨": 0, "당황": 1, "분노": 2, "불안": 3, "상처": 4, "슬픔": 5, "중립": 6 } - kore2en = { "기쁨": "joy", "당황": "surprise", "분노": "anger", "불안": "fear", "상처": "hurt", "슬픔": "sadness", "중립": "neutral" }
Downloads · 30 days
6
1% of all-time downloads
All-time downloads
990
Public
Parameters
278M
12.3 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors1.1 GB · 98%
From the Hugging Face model README
And.. this dataset doesn't have neutral class..
So additional dataset is used.
ref: https://aihub.or.kr/aihubdata/data/view.do?dataSetSn=271
finally I Concatenate 2 Datasets.
(example) [USR] 안녕. [BOT] 안녕하세요! 무엇을 도와드릴까요? [USR] 별일 없어.
이 두개의 특수 토큰은 반드시 사용해주시길 부탁드립니다.
And these are a part of real data.

and confusion matrix like this..

and so on.. F1, Accuracy