Stars
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Collaborative cheatsheets for console commands 📚.
High performance self-hosted photo and video management solution.
Open-source scientific and technical publishing system built on Pandoc.
Seamless operability between C++11 and Python
The open source mesh processing python library
Monorepo hosting the proton web clients
🐳 A curated list of Docker resources and projects
A curated list of amazingly awesome open-source sysadmin resources.
A list of Free Software network services and web applications which can be hosted on your own servers
Empowering everyone to build reliable and efficient software.
Flipper Zero firmware source code
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Open clone of OpenAI's unreleased WebText dataset scraper. This version uses pushshift.io files instead of the API for speed.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
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.
A tool for extracting plain text from Wikipedia dumps
The simplest, fastest repository for training/finetuning medium-sized GPTs.
QLoRA: Efficient Finetuning of Quantized LLMs
A straightforward collection of Music Generation research resources.
📋 A list of open LLMs available for commercial use.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.