Instructions to use darshandugar/MailClassifier-DistilBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use darshandugar/MailClassifier-DistilBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="darshandugar/MailClassifier-DistilBERT")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("darshandugar/MailClassifier-DistilBERT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update config.json
Verified signature0e680db
-
Update README.md
Verified signature# Corporate Email Categorization Model This is a fine-tuned DistilBERT model for classifying corporate emails into various categories. ## Overview This project focuses on building a robust model for corporate email categorization to automate the sorting and routing of internal and external communications. The process involves standard NLP techniques, data augmentation for handling class imbalance, and fine-tuning a pre-trained transformer model. ## Approach and Methodology The fine-tuning process for this model followed these key steps: 1. **Data Loading**: The initial dataset was loaded from the specified source. 2. **Exploratory Data Analysis (EDA)**: Basic EDA was performed to understand the data structure, identify missing values, and analyze the distribution of labels. 3. **Handling Data Imbalance**: It was observed that some categories had significantly fewer examples than others. To address this, data augmentation was employed. 4. **Artificial Data Generation**: Synthe…cd8d1f6 -
Upload folder using huggingface_hub
Verified signatureb03b9ca -
initial commit
Verified signaturefd34163