Utils for Unsloth https://github.com/unslothai/unsloth

The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

llama.cpp fork with additional SOTA quants and improved performance

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

LLM inference in C/C++

An extension for oobabooga/text-generation-webui that enables the LLM to search the web

Fast and lightweight DOM diffing/patching (no virtual DOM needed)

Python package wrapping llama.cpp for on-device LLM inference

Writing Extension for Text Generation WebUI

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

llama3 implementation one matrix multiplication at a time

Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors, now in oobabooga text generation webui!

Memoir+ a persona memory extension for Text Gen Web UI.

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…

Tools for merging pretrained large language models.

🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers

Science-driven chatbot development

Official implementation of Half-Quadratic Quantization (HQQ)

AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, D…

Distribute and run LLMs with a single file.

A web search extension for Oobabooga's text-generation-webui (now with nougat)

Fast and memory-efficient exact attention - Windows wheels

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Simple extension for text-generation-webui that injects recent conversation history into the negative prompt with the goal of minimizing the LLM's tendency to fixate on a single word, phrase, or se…

Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.

A coding agent for open models like Kimi K3