Free open-source modern C++17 / C++20 framework to create console, GUI (forms like WinForms) and unit test applications and libraries on Microsoft Windows, Apple macOS and Linux.

LLM training in simple, raw C/CUDA

CUDA on non-NVIDIA GPUs

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

🦜🔗 Build context-aware reasoning applications

A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Go ahead and axolotl questions

A high-throughput and memory-efficient inference and serving engine for LLMs

QLoRA: Efficient Finetuning of Quantized LLMs

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…

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Universal LLM Deployment Engine with ML Compilation

Stable Diffusion and Flux in pure C/C++

A high-throughput and memory-efficient inference and serving engine for LLMs

Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🔊 Text-Prompted Generative Audio Model

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

StableLM: Stability AI Language Models

Curated list of useful LLM / Analytics / Datascience resources