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
Request Inference Provider support for Zuzu02/boomkamae-bert-error-classifier
Hi! I'd like to request Inference Provider support for my text-classification model.
Model: Zuzu02/boomkamae-bert-error-classifier
Base model: tohoku-nlp/bert-base-japanese-v3
Task: text-classification (8 classes)
Size: ~0.1B parameters (small, fast inference)
Language: Japanese
Library: transformers + safetensors
Use case: This model classifies Japanese grammar errors in an educational app (BoomKamae) for university students learning Japanese (JLPT N5-N4). It detects error types like particle errors, word order, verb form, etc.
Why it matters: The app is part of a university thesis project. The model is already trained and published, but I can't use it in production because no Inference Provider supports it. The current fallback is rule-based, which is less accurate.
Providers I'm interested in: Novita, Together, Hyperbolic β any provider that supports text-classification with BERT models.
Thank you for considering! π