A react-based starter app for using the Multimodal Live API over websockets with Gemini

A course on aligning smol models.

🙌 OpenHands: Code Less, Make More

AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ

Agentic components of the Llama Stack APIs

Inference code for CodeLlama models

Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.

PyTorch extensions for high performance and large scale training.

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

An annotated implementation of the Transformer paper.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

Unsupervised text tokenizer for Neural Network-based text generation.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

Structured Text Generation

structured outputs for llms

Neural Networks: Zero to Hero

LLM training in simple, raw C/CUDA

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

A programming framework for agentic AI 🤖 (PyPi: autogen-agentchat)