Instructions to use Yacine75/question-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Yacine75/question-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Yacine75/question-classifier")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Yacine75/question-classifier") model = AutoModelForSequenceClassification.from_pretrained("Yacine75/question-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
🤗 DistilBERT - Classification de Questions
Ce modèle est un DistilBERT fine-tuné pour classifier les requêtes en :
- question_rag → ex: "How can I enroll in the Python course?"
- send_message → ex: "Send a message to my friend."
📌 Comment l'utiliser ?
from transformers import pipeline
classifier = pipeline("text-classification", model="Yacine75/question-classifier")
result = classifier("How can I enroll in the Python course?")
print(result)
📊 Performances
- Accuracy : 97.8%
- Validation Loss : 0.0246
📌 Détails de l'entraînement
- Modèle de base :
distilbert-base-uncased - Tâche : Classification binaire (
question_rag/send_message) - Dataset : 98 exemples annotés
- Époques : 3
- Optimiseur : AdamW
- Batch size : 8
🚀 Liens utiles
- Downloads last month
- 2