Update README.md

README.md

@@ -42,6 +42,22 @@ KorSciDeBERTa는 Microsoft DeBERTa 모델의 아키텍쳐를 기반으로, 논
 
 - Mecab 설치 참고: 다음 링크에서 '사용방법'. https://aida.kisti.re.kr/model/9bbabd2d-6ce8-44cc-b2a3-69578d23970a
 
+- Colab 사용하는 경우 Mecab 설치:
+
+<pre><code>
+! git clone https://github.com/SOMJANG/Mecab-ko-for-Google-Colab.git
+% cd Mecab-ko-for-Google-Colab/
+! bash install_mecab-ko_on_colab_light_220429.sh
+
+</code></pre>
+
+- ImportError: accelerate>=0.20.1 에러 발생시 해결법
+
+!pip install -U accelerate; pip install -U transformers; pip install pydantic==1.8
+
+: 설치 후 런타임 재시작
+
+
 2. git clone https://huggingface.co/kisti/korscideberta; cd korscideberta
 
 - **korscideberta-abstractcls.ipynb**
@@ -52,7 +68,7 @@ from transformers import AutoModelForSequenceClassification
 
 
 tokenizer = DebertaV2Tokenizer.from_pretrained("kisti/korscideberta")
-model = AutoModelForSequenceClassification.from_pretrained("kisti/korscideberta", num_labels=6, hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1)
+model = AutoModelForSequenceClassification.from_pretrained("kisti/korscideberta", num_labels=7, hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1)
 #model = AutoModelForMaskedLM.from_pretrained("kisti/korscideberta")
 ''''''
 train_metrics = trainer.train().metrics