My own version of the amazing Karpathy's project with architectural and training options changes

LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Load local LLMs effortlessly in a Jupyter notebook for testing purposes alongside Langchain or other agents. Contains Oobagooga and KoboldAI versions of the langchain notebooks with examples.

⚡ Building applications with LLMs through composability ⚡

A template to run LLaMA in Cog

Code for training & inference with FLAN family of models

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

Run, build, test transformer models using docker

Alpaca dataset from Stanford, cleaned and curated

Instruct-tune LLaMA on consumer hardware

🧠 A study guide to learn about Transformers

data related codebase for polyglot project

Fine-tuning 6-Billion GPT-J (& other models) with LoRA and 8-bit compression

Models built with TensorFlow

A JavaScript library dedicated to graph drawing