Update README.md

README.md

@@ -3,12 +3,7 @@ library_name: transformers
 tags: []
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
+# HowRU-KoELECTRA-Emotion-Classifier
 ## Model Details
 
 ### Model Description
@@ -16,10 +11,10 @@ tags: []
 이 모델은 한국어 일상 텍스트(특히 일기/심리 기록)에 나타나는 감정을 자동으로 분류하기 위해 구축된 감정 분류 모델입니다.
 기반 모델은 monologg/koelectra-base-v3-discriminator이며, 감정 분석 Task에 최적화되도록 8개 감정 라벨(기쁨, 설렘, 평범함, 놀라움, 불쾌함, 두려움, 슬픔, 분노) 구조로 파인튜닝되었습니다.
 
-- **Model type:** [Text Classification (Emotion Recognition)]
-- **Language (NLP):** [Korean (한국어, ko)]
-- **License:** [MIT]
-- **Finetuned from model:** [monologg/koelectra-base-v3-discriminator]
+- **Model type:** Text Classification (Emotion Recognition)
+- **Language (NLP):** Korean (한국어, ko)
+- **License:** MIT
+- **Finetuned from model:** monologg/koelectra-base-v3-discriminator
 
 ### Emotion Classes
 
@@ -69,26 +64,26 @@ print(predict("오늘 하루가 유난히 힘들고 지쳤다."))
 1. [LimYeri/kor-diary-emotion_v2]("https://huggingface.co/datasets/LimYeri/kor-diary-emotion_v2")
 2. [qowlsdud/CounselGPT]("https://huggingface.co/datasets/qowlsdud/CounselGPT")
 
-- **Total(8:2로 분할):** [50,000행]
-- **Train:** [40,000행]
-- **Validation:** [10,000행]
+- **Total(8:2로 분할):** 50,000행
+- **Train:** 40,000행
+- **Validation:** 10,000행
 
 ### Training Procedure
 
 - **Base Model**: [monologg/koelectra-base-v3-discriminator]("https://huggingface.co/monologg/koelectra-base-v3-discriminator")
-- **Objective**: [Single-label classification]
-- **Precision**: [fp16 mixed precision]
-- **Max Length**: [512]
+- **Objective**: Single-label classification
+- **Precision**: fp16 mixed precision
+- **Max Length**: 512
 
 #### Training Hyperparameters
 
-- **num_train_epochs**: [3]
-- **learning_rate**: [3e-5]
-- **weight_decay**: [0.02]
-- **warmup_ratio**: [0.15]
-- **per_device_train_batch_size**: [32]
-- **per_device_eval_batch_size**: [64]
-- **max_grad_norm**: [1.0]
+- **num_train_epochs**: 3
+- **learning_rate**: 3e-5
+- **weight_decay**: 0.02
+- **warmup_ratio**: 0.15
+- **per_device_train_batch_size**: 32
+- **per_device_eval_batch_size**: 64
+- **max_grad_norm**: 1.0
 
 ---
 
@@ -101,23 +96,35 @@ print(predict("오늘 하루가 유난히 힘들고 지쳤다."))
 | **Eval Loss**     | 0.16  |
 
 ---
-
 ## Model Architecture
 
 ### 1) ELECTRA Encoder (Base-size)
 
-- **Hidden size:** [768]
-- **Layers:** [12 Transformer blocks]
-- **Attention heads:** [12] 
-- **MLP intermediate size:** [3072]  
-- **Activation:** [GELU]  
-- **Dropout:** [0.1]  
+- **Hidden size:** 768
+- **Layers:** 12 Transformer blocks
+- **Attention heads:** 12
+- **MLP intermediate size:** 3072
+- **Activation:** GELU
+- **Dropout:** 0.1
 
 ### 2) Classification Head
 
 감정 8개 클래스를 예측하기 위한 추가 분류 헤드:
 
-- **Dense Layer**: [768 → 768]
-- **Activation**: [GELU]
-- **Dropout**: [0.1]
-- **Output Projection**: [768 → 8]
+- **Dense Layer**: 768 → 768
+- **Activation**: GELU
+- **Dropout**: 0.1
+- **Output Projection**: 768 → 8
+
+---
+
+## Citation
+```bibtex
+@misc{HowRUEmotion2025,
+  title={HowRU KoELECTRA Emotion Classifier},
+  author={Lim, Yeri},
+  year={2025},
+  publisher={Hugging Face},
+  howpublished={\url{https://huggingface.co/LimYeri/HowRU-KoELECTRA-Emotion-Classifier}}
+}
+```