Stars
The simplest, fastest repository for training/finetuning small-sized VLMs.
llama.cpp fork with additional SOTA quants and improved performance
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.
Command-line program to download image galleries and collections from several image hosting sites
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
A ⚡lightweight⚡ frontend for Google's Gemini Pro.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
NNT Neural Network Toolkit Custom Nodes for ComfyUI
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Official inference framework for 1-bit LLMs
Convert Compute And Books Into Instruct-Tuning Datasets! Makes: QA, RP, Classifiers.
A library for mechanistic interpretability of GPT-style language models
Evaluate your LLM's response with Prometheus and GPT4 💯
Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Ext…
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
An unsupervised model merging algorithm for Transformers-based language models.
zappityzap / zccz
Forked from artyfacialintelagent/CloneCleanerOpinionated fork of CloneCleaner, an extension for Automatic1111 which inserts random names, nationalities, hair styles and hair colors into your prompts.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
A simple prototype of an evolutionary system for improving Large Language Models.
Tools for merging pretrained large language models.
Open-source Windows and Office activator featuring HWID, Ohook, TSforge, KMS38, and Online KMS activation methods, along with advanced troubleshooting.
Code for NeurIPS 2023 paper "Restart Sampling for Improving Generative Processes"
The Prodigy optimizer and its variants for training neural networks.
Windows compile of bitsandbytes for use in text-generation-webui.