Automated document classification system using PyTorch & TorchText. Loads and preprocesses news articles, trains a text classification model, visualizes embeddings, and predicts topics such as World, Sports, Business, and Sci/Tech.

Fine-tuned BERT on AG News dataset to classify headlines into 4 categories achieving 87.40% accuracy.

End-to-end MLOps pipeline for news classification — experiment tracking with MLflow, data versioning with DVC, FastAPI serving, drift monitoring with Evidently AI, and a 4-job GitHub Actions CI/CD that builds and pushes to DockerHub on every commit.

End-to-end NLP text classification pipeline on AG News, a custom LLaMA-inspired transformer with RoPE/RMSNorm/SwiGLU, Optuna + MLflow hyperparameter tuning, uncertainty-aware evaluation, bundle promotion, FastAPI serving, and Streamlit dashboard. Deployable via Docker & HF Spaces.

Fine-tuned GPT-2 on AG News for news classification, with reproducible preprocessing, training, evaluation, and FP32 vs INT8 / 4-bit inference comparison.

Fine-tuned BERT (bert-base-uncased) model for multi-class news topic classification using the AG News dataset. Achieved 94.8% accuracy and deployed as an interactive web app via Streamlit.

NLP homework project covering AG News classification with BPE, Word2Vec and MLP, plus character-level LSTM generation of dinosaur names.

A Streamlit-based web app for classifying news articles into World, Sports, Business, or Sci/Tech using Logistic Regression and Neural Network models trained on the AG News dataset.

Parameter-efficient fine-tuning of DistilBERT using LoRA for sentiment and topic classification, with CLI, API, and interactive chatbot interfaces.