Train transformer language models with reinforcement learning.

Automatic headphone equalization from frequency responses

Software to automate the management and configuration of infrastructure and applications at scale.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Postgres CLI with autocompletion and syntax highlighting

Exploitation Framework for Embedded Devices

Structured Outputs

Deduplicating archiver with compression and authenticated encryption.

A MNIST-like fashion product database. Benchmark 👇

structured outputs for llms

📝 A text file containing 479k English words for all your dictionary/word-based projects e.g: auto-completion / autosuggestion

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

A command-line tool to download photos from iCloud

ImageBind One Embedding Space to Bind Them All

The property-based testing library for Python

A set of tools to keep your pinned Python dependencies fresh.

A template for PostgreSQL High Availability with Etcd, Consul, ZooKeeper, or Kubernetes

Ajenti Core and stock plugins

Very efficient backup system based on the git packfile format, providing fast incremental saves and global deduplication (among and within files, including virtual machine images). Please post prob…

A lightweight library for converting complex objects to and from simple Python datatypes.

Your self hosted YouTube media server

Real-time monitor and web admin for Celery distributed task queue

Repo for external large-scale work

📂 🐇 🎩 See what a program does before deciding whether you really want it to happen (NO LONGER MAINTAINED)

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

One webpage for every book ever published!

A system for quickly generating training data with weak supervision

A Python module to bypass Cloudflare's anti-bot page.

Redis-based components for Scrapy.