Instructions to use Zuzu02/boomkamae-bert-error-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Zuzu02/boomkamae-bert-error-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Zuzu02/boomkamae-bert-error-classifier")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Zuzu02/boomkamae-bert-error-classifier") model = AutoModelForSequenceClassification.from_pretrained("Zuzu02/boomkamae-bert-error-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
BoomKamae BERT Error Classifier V1
Modelo BERT japon茅s fine-tuneado para detectar errores gramaticales en oraciones japonesas.
Arquitectura
BertForSequenceClassification
N煤mero de clases
8
Clases
- CORRECT
- PARTICLE_ERROR
- WORD_ORDER
- VERB_FORM
- MISSING_ELEMENT
- ADJECTIVE_ERROR
- EXTRA_ELEMENT
- SEMANTIC_ERROR
Resultados V1 sobre TEST
- Accuracy: 76.67%
- Precision Macro: 75.51%
- Recall Macro: 57.45%
- F1 Macro: 58.83%
- Test Loss: 1.5281
Configuraci贸n
- Base: tohoku-nlp/bert-base-japanese-v3
- Epochs: 5
- Learning rate: 2e-5
- Batch size: 8
- Weight decay: 0.01
- Max length: 128
- Tipo: clasificaci贸n multiclase de una sola etiqueta
- Downloads last month
- 72
Model tree for Zuzu02/boomkamae-bert-error-classifier
Base model
tohoku-nlp/bert-base-japanese-v3