This project is designed to extract text from documents and prepare it for processing by Large Language Models (LLM).

LLM-based mutation testing

《多模态大模型：新一代人工智能技术范式》作者：刘阳，林倞

The framework for fast development and deployment of RAG systems.

This is a RAG implementation using Open Source stack. BioMistral 7B has been used to build this app along with PubMedBert as an embedding model, Qdrant as a self hosted Vector DB, and Langchain & Llama CPP as an orchestration frameworks.

DriveLM: Driving with Graph Visual Question Answering

Your Private Companion. The future AGI takeover starts here!

Franklin is a LLM powered AI IRC chat bot

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

Explain a black-box module in natural language.

Experiment a differentially private decoding strategy for Large Language Models.

A codebase for "Language Models can Solve Computer Tasks"

Space Model framework that allows for maintaining generalizability, and enhances the performance on the downstream task by utilizing task-specific context attribution. It is an external LLM layer, that improves accuracy in classification task for multiple datasets, such as HateXplain, IMDB movies reviews and more.

A Scalable and Explainable Approach to Discriminating Between Human and Artificially Generated Text

Image Generator is a dynamic platform designed to provide users with an immersive and innovative experience in image generation. Through our utilization of open-source models, particularly leveraging Hugging Face and its API calls, we offer a unique approach to creating and manipulating images based on textual prompts.

I developed a PyTorch_For_PoorGuys framework and Let it train LLM on NVIDIA GeForce 2080Ti GPU as my Bachelor's Graduation Design Project

"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases" by Jiarui Li and Ye Yuan and Zehua Zhang

CTF challenges designed and implemented in machine learning applications

Flask application for sentiment detection using LLMs

Open source implementation of Sova - RAG-based Web search engine using power of LLMs. Using Langchain, Ollama, HuggingFace Embeddings and scraping google search results.