Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Unattended Lightweight Text Classifiers with LLM Embeddings

Faster, smaller BERT models in just a few lines of code.

Lightweight cross-lingual coreference resolution with spaCy using ONNX Runtime inference of transformer models.

Ash — offline survival assistant for iOS. Gemma 4 E2B/E4B fully on-device (text · image · voice) with RAG-grounded answers over 56 emergency-response packs. Built for the Kaggle Gemma 4 Good Hackathon.

Twitter Sentiment Analysis using all-MiniLM-L6-v2 embeddings.

Biomedical RAG Tool for Gene - Disease Association

End-to-end multi-agent research system with 6 specialized agents (Planner, Search, Scraper, Retriever, Writer, Evaluator) to separate task planning, live source discovery, grounded synthesis, and output evaluation.

This repository serves as the RAG Project MiniLM Model from Microsoft named as sentence-transformers/all-MiniLM-L6-v2 as the embedding model for my resume , and utilizing OpenAI to answer questions based on the Resume

Dashboard Streamlit de scoring crédit explicable + veille NLP comparative BERT vs MiniLM pour la classification de produits e-commerce.

comprehensive solutions for Adobe's Document Intelligence Hackathon 2025, encompassing two distinct challenges focused on advanced PDF processing and persona-driven content analysis. Both implementations adhere to stringent performance requirements including sub-60-second execution times and containerized deployment within 1GB resource constraints

Same model, same hardware: an apples-to-apples Rust embedding benchmark across fastembed, ort, candle, ollama, and llama-cpp-2.

RAG pipeline vs rules-based chatbot for university FAQs. Built with FAISS, GPT-3.5, Python REST API, and deployed via Anvil.

A state-of-the-art Retrieval-Augmented Generation (RAG) system with hybrid search, multi-hop reasoning, answer verification, and source citation — delivering accurate, trustworthy, and context-aware answers from large document collections.

Fully local and open-source AI study companion for lecture PDFs - with slide summarization, smart Q&A, and flashcard creation using LangChain and Hugging Face Transformers.

Prototype of a customizable local AI assistant demonstrating modular architecture, secure workspace design, and retrieval-based conversations.

A modular RAG pipeline for health question answering using vetted sources (CDC, NIH, Mayo, WHO). Retrieval is powered by TF‑IDF or MiniLM embeddings, and generation uses a controlled Qwen LLM stub.

A semantic quote retrieval system using fine-tuned MiniLM, FAISS indexing, and RAG-style LLM synthesis-built with Streamlit and Hugging Face Spaces.

Advanced NLP project detecting duplicate questions on Quora using transformer-based embeddings, LSTM architectures, and ensemble models, achieving 88% accuracy with scalable solutions for real-world applications 🧠💬.

Ask anything out loud or by typing, and a warm companion with a friendly face reads Wikipedia facts back to you using small local models.