Stars
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Run Generative AI models directly on your hardware
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Pika Backup – 🪞 Mirror only 🪞 – See https://gitlab.gnome.org/World/pika-backup for development
Chat over Telegram on a modern and elegant client
Training and Working with LLMs on a Single GPU
Bluetooth Forward and Future Secrecy Attacks and Defenses (BLUFFS) [CVE 2023-24023]
An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
AI tutor powered by Theory-of-Mind reasoning
A guidance language for controlling large language models.
A language for constraint-guided and efficient LLM programming.
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
StableLM: Stability AI Language Models
A toolkit for developing and comparing reinforcement learning algorithms.
Multi-Joint dynamics with Contact. A general purpose physics simulator.
Awesome-LLM: a curated list of Large Language Model
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
High throughput synchronous and asynchronous reinforcement learning
Benchmark environments for reward modelling and imitation learning algorithms.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

