MetaMate: Large Language Model to the Rescue of Automated Data Extraction for Educational Systematic Reviews and Meta-analyses

Models and examples built with TensorFlow

DataComp for Language Models

LLM101n: Let's build a Storyteller

Members of the United States Congress, 1789-Present, in YAML/JSON/CSV, as well as committees, presidents, and vice presidents.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

Open source codebase powering the HuggingChat app

Source code for Twitter's Recommendation Algorithm

Open-source vector similarity search for Postgres

state-of-the-art search over vector embeddings and structured data (SIGMOD '24)

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes

Video+code lecture on building nanoGPT from scratch

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

Port of Facebook's LLaMA (Large Language Model Meta AI) in Golang with embedded C/C++

Streamlit — A faster way to build and share data apps.

LM Studio TypeScript SDK (pre-release public alpha)

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Jupyter Notebooks to help you get hands-on with Pinecone vector databases

GitHub Action that wraps the flyctl

Redis Vector Library (RedisVL) interfaces with Redis' vector database for realtime semantic search, RAG, and recommendation systems.

Local first semantic code search and chat powered by vector embeddings and LLMs

🚀 Cookiecutter Template for FastAPI + React Projects. Using PostgreSQL, SQLAlchemy, and Docker

Visual and semantic vector similarity with Redis Stack, FastAPI, PyTorch and Huggingface.

Build a semantic search engine with Transformers and Faiss

Search Your PDF App using Langchain, ChromaDB, Sentence Transformers, and LaMiNi LM Model. This app is completely powered by Open Source Models. No OpenAI key is required.

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.