minilm

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.

Text Mining (PubMed Search) with NLP & LLM

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

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

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 🧠💬.

A demo from the blog post comparing MiniLM-based models using song lyrics and Milvus for vector similarity search—an approach that works for any text content.

An AI-powered study companion that helps students understand lecture material through intelligent question answering, slide summarization, PDF summaries, and flashcard generation. Built with LangChain, Hugging Face Transformers, and Gradio — and fully powered by open-source LLMs running on your local GPU.

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

An Ai-powered agent that automatically clusters, summarizes and prioritizes operational asset alerts . made using Python , sentence-transformers(MiniLM) and Hugging Face integration in Streamlit-ui -- helping engineering and operations teams focus on what matters most.

PaperMind AI is a local privacy-first PDF assistant that allows natural language chat with any document. Powered by FAISS, LangChain, MiniLM embeddings, and TinyLLaMA 1.1B — all running offline. Built with FastAPI backend and a clean HTML/CSS/JS frontend.

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