Lists (1)
Sort Name ascending (A-Z)
Starred repositories
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
Speech modality adapter for pretrained LLMs using neural audio codecs (Mimi/DAC).
The home of Carbon Genomic Foundation Model 🧬
LLaDA2.0-Uni: Understanding and Generation the World.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
SLMS is an open-source research project that integrates Regular Transformers with biologically-inspired Spiking Neural Networks to develop efficient 1B-parameter language models.
Depix is a PoC for a technique to recover plaintext from pixelized screenshots.
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
A character-level language diffusion model trained on Tiny Shakespeare
The official Python SDK for the Perceptron API
A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.
The official implementation of OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
A powerful 130-million-parameter model trained from scratch as part of a truly open-source stack, including a custom tokenizer, dataset, and optimizer.
Qwen-Image text to image lora trainer
The simplest, fastest repository for training/finetuning small-sized VLMs.
Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling