Stars
Micro Llama is a small Llama based model with 300M parameters trained from scratch with $500 budget
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
A simple, easy-to-hack GraphRAG implementation
GraphRAG / From Local to Global: A Graph RAG Approach to Query-Focused Summarization
Curated list of useful LLM / Analytics / Datascience resources
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…
Curated list of awesome GAN applications and demo
This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive A…
TauFactor is a parallelised solver for calculating tortuosity factors from voxel data.
Generate NFT or train new model in just few clicks! Train as much as you can, others will resume from checkpoint!
Local version of samba-web, a trainable segmentation web app with deep learning powered labelling
A curated list of resources for using LLMs to develop more competitive grant applications.
Extract clean data from anywhere, powered by vision-language models ⚡
Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Adding guardrails to large language models.
PyPaperBot is a Python tool for downloading scientific papers using Google Scholar, Crossref, SciHub, and SciDB.